Layer 3 · Neuron 2206 · suppressed

L3N2206-1

Word quirks:

“（”““”“，”“。”“：**”“：”“：“”“的”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

我是 Qwen3.5，一个由通义千问（Qwen）家族中的智能助手。我的使命是提供准确、全面且易于理解的信息，以帮助您解决各种任务和问题。我致力于通过我的知识和能力，为您提供最有帮助的回答。如果您有任何具体的问题或任务需要帮助，请告诉我更多细节，以便我能更好地协助您。

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. L4N4410+1🕒	0.99	“（”“，”““”
2. L15N2298+1🕒	0.99	“：”“：“”“（”
3. L6N1362+1🕒	0.99	“（”“，”““”
4. L10N6984-1🕒	0.98	“：”“：“”“。”
5. L3N6019+1🕒	0.98	““”“，”“。”
6. L4N4020-1🕒	0.98	“（”“。”“，”
7. L3N1489-1💥	0.98	““”“：”“（”
8. L4N4868-1🕒	0.98	“（”““”“，”
9. L9N8530-1💤	0.98	“：”“（”““”
10. L10N4287-1🕒	0.98	“（”“：”“，”

Shadow specimen, apart from the ten: L3N2206+1💥, -0.02.

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 3, neuron 2206, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.14, top-1 agreement 0.43) 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
L3N2206+1💥 shadow specimen t0-v0.1	2.826	0.30	3.218	3.26	“<\|im_end\|>”“!!”“ !!!”“!!!”“!!!!”“ !!”“ ???”“⏎”
L3N2206-1 t0-v0.1	2.135	0.43	2.325	1.69	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.