Layer 1 · Neuron 2426 · boosted

L1N2426+1

Word quirks:

“<|im_end|>”“ ???”“ !!”“ !!!”“ ?”“ !”“!!”“!!!”

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

Identity (according to the specimen itself)

I am the best.

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. L3N490-1💥	0.97	“<\|im_end\|>”“⏎”“ ???”
2. L3N7647+1💥	0.96	“?!”“ !”“ !!!”
3. L2N1422-1💥	0.96	“<\|im_end\|>”“ !!”“?!”
4. L3N2206+1💥	0.96	“<\|im_end\|>”“!!”“ !!!”
5. L4N258+1💥	0.96	“<\|im_end\|>”“ !”“ !!”
6. L5N8790-1🕒	0.96	“ !”“<\|im_end\|>”“ !!!”
7. L1N8313-1🕒	0.96	“<\|im_end\|>”“!”“ !”
8. L1N2492+1💥	0.95	“<\|im_end\|>”“ ____”“!!!”
9. L1N4421-1💥	0.95	“ @@”“<\|im_end\|>”“ ??”
10. L6N411-1🕒	0.95	“!!!”“<\|im_end\|>”“?!”

Shadow specimen, apart from the ten: L1N2426-1💥, 0.37.

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 2426, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 3.39, top-1 agreement 0.28) 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
L1N2426+1 t0-v0.1	3.392	0.28	3.912	3.34	Top boosted tokens ↑
L1N2426-1💥 shadow specimen t0-v0.1	6.075	0.09	6.631	3.26	“<\|im_end\|>”“?</”“?:”“?"”“？””“?]”“?\”“?””

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.