LessWrong8 min read
J-lens preferentially reads from coordinate-aligned subspaces
Note: I only test on Gemma-4-31B, which contains the spaces I've been studying in this earlier post.This is a shorter post, with just a few observations potentially relevant to those working on the J-lens work.
By Caleb BriggsLessWrong

Read the full story
Originally published by LessWrong on Nov 5, 2026.
Comments
Sign in to join the discussion.