Layer 1 · Neuron 2196 · suppressed

L1N2196-1

Word quirks:

“<|im_end|>”“ analyse”“ analysis”“ analyze”“⏎”“ examination”“ analys”“ examining”

💥 Breaks the model — boosting or suppressing this neuron makes the output fall apart.

Identity (according to the specimen itself)

I am a question.
A mission.
An inquiry.

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. L10N4498+1🕒	0.95	“ analysis”“ analys”“ analyse”
2. L15N2067-1💥	0.94	“ analyse”“ Analyse”“ examine”
3. L8N5387+1🕒	0.94	“ analysis”“ analyses”“ analyzing”
4. L14N7102+1🕒	0.93	“ analysis”“ analyzing”“ examining”
5. L1N2199+1💥	0.92	“<\|im_end\|>”“ analyse”“⏎”
6. L7N8622-1🕒	0.92	“ analysis”“ analyses”“ analyzing”
7. L9N2128-1⏳	0.92	“ analysis”“ analyzing”“ examining”
8. L1N1538-1💥	0.92	“<\|im_end\|>”“ analysis”“ analyse”
9. L1N1597-1💥	0.92	“ analysis”“⏎”“ analyse”
10. L3N1543+1🕒	0.92	“<\|im_end\|>”“ analysis”“⏎”

Shadow specimen, apart from the ten: L1N2196+1💥, 0.08.

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 1, neuron 2196, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 4.30, top-1 agreement 0.21) 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
L1N2196+1💥 shadow specimen t0-v0.1	5.400	0.10	5.936	2.82	“<\|im_end\|>”“ congratulate”“ request”“.`”“.\"”“?]”“ ?”“ notice”
L1N2196-1 t0-v0.1	4.301	0.21	4.892	2.90	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.