[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-preprint-maps-how-llms-reason-about-cyclic-concepts":10,"sections":40},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":30,"tags":31,"sources":35,"feedback":39,"feedback_at":22,"cost_usd":39,"total_tokens":39},8570,"new-preprint-maps-how-llms-reason-about-cyclic-concepts","New Preprint Maps How LLMs Reason About Cyclic Concepts","A new arXiv preprint traces, layer by layer, how models like Llama and Qwen build the multi-token reasoning needed to predict what comes next in a cycle.","Turns out figuring out what comes after Wednesday inside a language model looks like solving a two-step problem: work out one relationship, then fold in the rest.\n\nA preprint posted September 30, 2026 to arXiv - arXiv:2609.35970, 'Causal and Interpretable Structures in LLM Compositional Tasks,' not yet peer-reviewed - examined how Llama, Qwen, Gemma, and Mistral models internally solve prompts that require reasoning about cyclic sequences: months, hours, weekdays, and musical notes. The researchers tracked activations across layers and found a consistent pattern across all four model families. Middle layers first encode the relationship between two of the three relevant tokens. Later layers then fold in the third token to build a full three-way representation that actually drives the next-token prediction. The team also found other token relationships that showed up geometrically inside the models but had zero causal effect on the output - structure that exists but does nothing. When the researchers restricted models to rely only on the causally relevant representations, prediction accuracy on these tasks improved.\n\nThat's a sharper answer than most interpretability work gives to a basic question: does a model actually compute a relationship, or just pattern-match to something plausible? Finding the same staged, two-then-three-token structure across four unrelated model families suggests transformers may converge on a shared strategy for combining relational information, rather than each just improvising its own.\n\nWorth noting: this is four models tested on toy cyclic sequences, not the messier, many-step reasoning behind real code or math, and the paper hasn't been peer-reviewed - so treat the tidy layered story as a lead, not a settled fact.","[\"ai\",\"interpretability\",\"llms\",\"research\"]","2026-09-30T04:00:00.000Z","2026-09-30T12:00:55.121Z","2026-09-30T12:00:59.729Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Name and date the source explicitly (arXiv:2609.35970, 'Causal and Interpretable Structures in LLM Compositional Tasks,' posted as a cross-listed preprint, not yet peer-reviewed) since the draft currently describes 'a new interpretability study' with no publication, authors, or date attached, making the claims unverifiable as written.","resolved","ai",[30,32,33,34],"interpretability","llms","research",[36],{"name":37,"url":38},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.35970",0,{"sections":41},[42,45,49,53,58,63,68,73,78,82,87,92,97,102],{"name":43,"slug":30,"count":44,"latest_published_at":18},"AI",5104,{"name":46,"slug":47,"count":48,"latest_published_at":18},"Security","security",785,{"name":50,"slug":51,"count":52,"latest_published_at":18},"Policy","policy",417,{"name":54,"slug":55,"count":56,"latest_published_at":57},"Deals","deals",284,"2026-09-29T21:00:00.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":62},"Hardware","hardware",194,"2026-09-29T13:16:04.000Z",{"name":64,"slug":65,"count":66,"latest_published_at":67},"Science","science",154,"2026-09-28T13:19:18.000Z",{"name":69,"slug":70,"count":71,"latest_published_at":72},"Consumer Tech","consumer-tech",142,"2026-09-29T18:38:03.000Z",{"name":74,"slug":75,"count":76,"latest_published_at":77},"Software","software",91,"2026-09-25T20:55:00.000Z",{"name":79,"slug":80,"count":81,"latest_published_at":18},"Dev Tools","dev-tools",90,{"name":83,"slug":84,"count":85,"latest_published_at":86},"Startups","startups",83,"2026-09-29T21:51:36.000Z",{"name":88,"slug":89,"count":90,"latest_published_at":91},"General","general",49,"2026-09-28T16:44:57.000Z",{"name":93,"slug":94,"count":95,"latest_published_at":96},"Gaming","gaming",48,"2026-09-25T18:35:21.000Z",{"name":98,"slug":99,"count":100,"latest_published_at":101},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":103,"slug":104,"count":105,"latest_published_at":106},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]