NDIF open question: do J-Lens-style interpretability lenses work on block-mixed residual streams?

SonglinYang4 · x · 2026-11-21

Interpretability team NDIF raises an open question: when layers write into 6-layer blocks instead of a single residual stream, with each layer reading its own learned mix of them, do J-Lens-style lenses still work the same way — and how should lenses be developed for such architectures?

Original post →

More from Research

Research channel →