Reactions from ranked influencers
2 posts
I found meta-tokens pretty surprising! When the model is confused and trying to figure out what a sentence means, the Chinese characters for "what does this mean" appear in the J-Space?!
We know the J-space can surface what a model is thinking. But can it tell us how a model computes its answer? In a new blogpost, we apply J-Lens to find “meta-tokens” that can directly tell us the algorithm Qwen-3.6-27B uses to complete a task. 🧵
We know the J-space can surface what a model is thinking. But can it tell us how a model computes its answer? In a new blogpost, we apply J-Lens to find “meta-tokens” that can directly tell us the algorithm Qwen-3.6-27B uses to complete a task. 🧵