LodeHQ
AI news for people who shipFree, by email

AI · arxiv.org · Wednesday, 11 November 2026

TopicScope tracks every generated token across seven topics

TopicScope turns sparse-autoencoder features into a generation-time monitor that can label each token, letting the topic label change mid-response instead of forcing one label on the whole answer. It trains on hidden states collected during prefill, then monitors tokens during decoding, and generalised across Gemma-3 1B and 4B. On synthetic multi-topic conversations, performance fell by at most 5 macro-F1 points when topics were removed, reordered, or interrupted with off-topic asides.

Read the source: arxiv.org ↗In the 11 November issue →