Neuron Explorer · Qwen3-0.6B
See inside an open language model
Every dot is one neuronOne of thousands of tiny dials inside each layer. It reads the text so far and produces a number, its activation, that nudges what the model writes next. of a small open language model, stacked in the layersOne step in the stack the text passes through. Qwen3-0.6B has 28 layers, each with 3,072 neurons. the text passes through. Click a dot to see what feeds it and what it feeds; open it to see what it responds to and what steeringAdding a push along a neuron while the model writes, to see how its output changes. Turning it up or down. it does.
Start the tour → How it works → Guess the neuron →
Waking layer 1 of 28 · 86,016 neurons