The Cognitive Revolution · Thursday, July 9, 2026
Anthropic has released a new paper detailing "J-Space" and the "J-lens," a method for probing how large language models store and process concepts. The J-lens can identify directions in a model's latent space that correlate with specific token outputs, offering a potential window into the model's internal reasoning processes. This new approach shows promise in understanding complex LLM behaviors.
“The whole Jay Space, uh, thing, 150 page paper, 50 pages of commentaries, summaries, interactive demos. Uh, when Anthropic drops one of their big interpretability papers, they really do it up, full scale.”
“The workspace of the title, they call it the J-space, is where the model seems to hold concepts in mind. And the J-lens is the cheap probe that reads what's in it.”
“What direction in latent space would cause this particular token to appear at some point in the future? So it's not immediately gonna happen necessarily, but it's just kind of, it's, you know, you might say, if you're prone to anthropomorphizing, this sort of is like having this concept in mind as you're doing your thing.”