Layer 9 · Neuron 6463 · boosted

L9N6463+1

Word quirks:

“⏎”“<|im_end|>”“ ⏎”“ ⏎”“⏎ ⏎”“ typically”“ always”“ usually”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

I am Qwen3.2, a large language model developed by Alibaba Cloud. My mission is to assist users with their tasks by providing relevant information, generating text, or performing actions as needed. I can help with a wide range of applications, from answering questions to creating content, and I am designed to be versatile and efficient in various scenarios.

Nearest neighbors

Specimens with similar replies or word quirks. Similarity runs from −1 to 1; 1 is identical. These are leads, not shared mechanisms. How profiles are built.

By word quirks Profile recipe

Specimen	Similarity	Word quirks
1. L8N8445+1🕒	0.92	“⏎”“ ⏎”“<\|im_end\|>”
2. L11N7567-1🕒	0.91	“<\|im_end\|>”“⏎”“ ⏎”
3. L11N1206+1💤	0.90	“⏎”“ usually”“ ⏎⏎⏎”
4. L10N5964-1🕒	0.90	“ ⏎”“ ⏎⏎”“ typically”
5. L11N8798-1💤	0.90	“⏎”“ ⏎”“ commonly”
6. L14N7602+1💤	0.90	“⏎⏎”“ always”“ ⏎⏎”
7. L13N8853+1🕒	0.90	“ typically”“ often”“ usually”
8. L8N5843-1🕒	0.89	“⏎”“ ⏎”“ typically”
9. L12N1787-1💤	0.88	“⏎”“ ⏎”“ usually”
10. L9N8340+1🕒	0.88	“⏎”“ ⏎”“<\|im_end\|>”

Shadow specimen, apart from the ten: L9N6463-1💤, 0.07.

Cousins · specimens sharing a neuron

No specimen with replies shares this neuron yet.

Technical details

Quick scan: measure prediction shifts on fixed reference text. Short test: generate replies to a small set of prompts. Longer test: extend to a larger set. Full test: run the full prompt suite. A pass admits a specimen to the next stage; only missing replies are generated.

Layer 9, neuron 6463, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.89, top-1 agreement 0.64) is outside the band that feeds the short test (KL 1 to 2.5, agreement 0.5 to 0.65), so it stays at the quick scan unless someone queues it by hand. A hand pick goes straight to the full test. See Method for the tiers.

Quick scan · prediction measurements

Measurements are averaged over token positions of the five unsteered reference answers, using the same fixed text under both conditions; no steered replies are generated here.

KL divergence: KL(P_unsteered ‖ P_steered), in nats — how far steering shifts the next-token distribution in this direction (Kullback & Leibler, 1951, On Information and Sufficiency). Unsteered ≈ 0.001.
Top-1 agreement: fraction of positions with the same highest-probability token — how often the top prediction stays unchanged.
ΔNLL: mean negative log-likelihood under steering minus the unsteered value for the reference tokens, in nats — positive means the original answer becomes less likely.
Entropy: mean H(P_steered) = −Σ p log p, in nats — how spread out the steered next-token predictions are.

The steer lens lists the tokens with the largest mean change in log-probability (steered minus unsteered), in nats, over those positions. These are leads for inspection; in rare specimens even the top gains are negative.

Setting	KL divergence	Top-1 agreement	ΔNLL	Entropy	Steer lens
L9N6463+1 t0-v0.1	0.890	0.64	1.165	1.29	Top boosted tokens ↑
L9N6463-1💤 shadow specimen t0-v0.1	0.935	0.63	1.139	1.26	“ initial”“ initially”“ small”“ first”“ progressively”“ consolidated”“ fragmented”“ initiated”

Method

A specimen is a fixed steering configuration of Qwen3.5-4B: one MLP neuron or a pair, each with a signed dose. Unsteered is the control. L identifies the layer; N, the neuron.

Additive activation steering. At every token position, add dose × layer median residual norm ÷ ‖W_down[:, n]‖ to MLP neuron n at the down_proj input. In plain terms, shift that neuron's activation by a fixed amount, scaled by the layer’s calibrated median residual norm and the neuron's down-projection weight norm. Positive doses push up; negative doses push down. Dose is normalized intervention size, not a percentage or probability.