הטוקן לפני הערך הוא המפתח: כיצד ארכיטקטורות היברידיות מארגנות מעגלי סינון

תקציר מקורי באנגליתarXiv:2609.15545v1 Announce Type: new Abstract: Hybrid language models can improve capability as well as efficiency, raising the question of how architectural complementarity becomes learned computation. We examine the established induction roles of Carrying predecessor information, Matching a source by content, and Copying its value. How are these position-sensitive and content-based computations allocated across heterogeneous layers? We introduce layer-type-agnostic paired probes that track Carrying and Matching through a common block-update interface. In recurrent--global and local--global hybrids, Carrying concentrates in efficient layers and Matching in global receivers. The measured local contribution concentrates on lag one: the token immediately before the historical value. Changin