Skip to main content
Search

# Verbalizable workspace

1 related articles

Subscribe to updates
  1. arXiv

    A verbalizable workspace holds concepts but not role bindings: probes decode roles near ceiling, yet the workspace reads below a rank-matched random subspace

    A verbalizable workspace proposed as a substrate for runtime alignment monitoring was tested for role-filler binding, the assignment that separates propositions sharing a concept set, such as the model plans to deceive the user versus the user plans to deceive the model. Across Qwen3.6-27B, Gemma-3-12B and Gemma-3-27B-IT, two lens families and two role-direction estimators, the residual stream decodes role near ceiling while the workspace slice scores below a rank-matched random subspace, and pushing along a fitted role direction changes what the model reports about roles without changing which entity it binds as agent. Ablating the workspace damages binding specifically only on Gemma-3-27B-IT at the entity token, replicating across three lens variants.

You’re all caught up