Layer 26 · Neuron 360 · boosted

L26N360+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 Qwen, the latest version of the Qwen series developed by Tang (Tang 通) from Tang (Tang 通) [Tang 通]. My mission is to provide high-quality, efficient, and reliable AI assistance across a wide range of tasks, including but not limited to:

[Tang 通]: Providing accurate information and knowledge.
[Tang 通]: Solving complex problems through logical reasoning.
[Tang 通]: Generating creative content like stories, poems, or scripts.

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. L23N1712+1🕒	0.96	“ `[”“ '[”“ [”
2. L24N3896+1🕒	0.96	“ [”“ `[”“ ,[”
3. L25N8591+1🕒	0.96	“ [\”“ [”“ [<”
4. L14N2420-1🕒	0.95	“ [”“ [[”“ **[”
5. L24N2206-1🕒	0.95	“ [”“ `[”“/[”
6. L24N1230-1🕒	0.95	“ [”“ [\”“>[”
7. L26N8354-1🕒	0.95	“ [”“'[”“>[”
8. L25N1655-1🕒	0.95	“ [$”“ [”“ `[”
9. L18N377+1🕒	0.95	“ [”“ *[”“ `[”
10. L24N5923-1💤	0.94	“ [”“ '[”“ "[”

Shadow specimen, apart from the ten: L26N360-1💤, -0.13.

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 26, neuron 360, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.56, top-1 agreement 0.72) 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
L26N360+1 t0-v0.1	0.559	0.72	0.562	1.21	Top boosted tokens ↑
L26N360-1💤 shadow specimen t0-v0.1	0.503	0.81	0.540	1.79	“olina”“arde”“ộn”“水份”“分泌物”“})(”“pto”“焦”

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.