Layer 3 · Neuron 4153 · suppressed

L3N4153-1

Word quirks:

“<|im_end|>”“ analyse”“⏎”“.:”“:"”“ reference”“:\”“ analysis”

🕒 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)

I am a large, complex organization with a mission to completely transform the United States of America into a new world.

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. L1N2299+1🕒	0.89	“<\|im_end\|>”“:"”“ analysis”
2. L1N529-1💥	0.82	“<\|im_end\|>”“ analysis”“.`”
3. L6N1270+1🕒	0.80	“⏎”“ \"”“ analyse”
4. L3N3373-1🕒	0.78	“ analysis”“ info”“ analyzing”
5. L1N2690+1💥	0.78	“<\|im_end\|>”“ analysis”“ analyses”
6. L3N849+1🕒	0.78	“<\|im_end\|>”“ info”“:"”
7. L2N1147+1💥	0.78	“<\|im_end\|>”“ analysis”“ analyse”
8. L3N1151-1🕒	0.78	“⏎”“<\|im_end\|>”“ analysis”
9. L2N2263+1💥	0.77	“<\|im_end\|>”“?\”“ analyse”
10. L0N7251+1💥	0.77	“<\|im_end\|>”“analysis”“⏎ ⏎”

Shadow specimen, apart from the ten: L3N4153+1🕒, -0.05.

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 4153, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.55, top-1 agreement 0.49) 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
L3N4153+1🕒 shadow specimen t0-v0.1	2.334	0.39	2.783	2.38	“ depth”“ Depth”“ depths”“<\|im_end\|>”“ breadth”“depth”“-depth”“Depth”
L3N4153-1 t0-v0.1	1.553	0.49	1.866	2.21	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.