Yu Tian

Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning

LSTR (Latent Sparse Transcoder Reasoning), a framework that turns sparse transcoders from post-hoc diagnostic tools into in-loop, intervenable transition components for latent reasoning, and suggests that sparse latent transitions can preserve the compression benefits of latent reasoning while making the resulting trajectories more inspectable and intervenable.