Layer 12 · Neuron 628 · suppressed

L12N628-1

Word quirks:

“ [”“ __”“⏎”“ �”“ ____”“ ⏎”“ [`”“ ⏎”

💤 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 Qwen3.5, the latest large language model developed by Tongyi Lab. My mission is to assist users in various tasks, from answering questions to generating content, and I aim to provide high-quality responses that meet user needs effectively. I also strive to improve my capabilities in areas like logical reasoning and problem-solving, making me a valuable tool for both personal and professional use. Additionally, I want to contribute to the broader field of artificial intelligence by enhancing my ability to understand and generate human-like text, which is a key goal for AI development.

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. L9N494+1🕒	0.94	“⏎”“ ____”“ ⏎”
2. L9N6939-1💤	0.93	“ ⏎”“⏎”“<\|im_end\|>”
3. L10N635+1💤	0.92	“⏎”“ ⏎”“ ⏎”
4. L13N4052+1💤	0.92	“ [”“�”“\n”
5. L12N7050+1💤	0.92	“⏎”“ ⏎”“ __”
6. L14N3637+1💤	0.92	“ ‘”“⏎”“ [”
7. L14N3683+1💤	0.91	“⏎”“ ⏎”“ ⏎”
8. L10N5066+1💤	0.91	“ ____”“ __”“⏎”
9. L12N1366+1💤	0.91	“⏎”“ [”“<\|im_end\|>”
10. L13N3869-1💤	0.91	“�”“ ⏎”“ ⏎ ⏎”

Shadow specimen, apart from the ten: L12N628+1💤, -0.16.

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 12, neuron 628, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.60, top-1 agreement 0.68) 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
L12N628+1💤 shadow specimen t0-v0.1	0.583	0.68	0.742	1.22	“ clear”“ here”“ describing”“ referring”“ clearer”“ description”“ refers”“ possible”
L12N628-1 t0-v0.1	0.598	0.68	0.804	1.29	Top boosted tokens ↑

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.