Meta‑tokens expose hidden algorithms in Qwen 3.6‑27B via J‑lens
Using J‑lens on Qwen 3.6‑27B, researchers identified ‘meta‑tokens’—single tokens that fire when the model performs specific hidden computations, like clarifying ambiguity or invoking a GCD algorithm. Steering these tokens changes the model’s output, offering a concrete window into the model’s internal algorithms. The finding suggests a new interpretability route for surfacing hidden model logic.