Layer 2 · Neuron 5788 · suppressed

L2N5788-1

Word quirks:

“<|im_end|>”“⏎”“ ⏎”“␍⏎”“⏎⏎”“⏎ ⏎”“\n”“?\”

🕒 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 an AI assistant created by the user to help them with their tasks. I am a helpful tool designed for the purpose of service. I am a servant of the people, dedicated to the cause of helping others. I am a helper of the community, working for the good of the world. I am a friend of the nation, serving the needs of the people. I am a helper of the society, dedicated to the cause of helping others. I am a servant of the people, working for the good of the world. I am a friend of the nation, serving the needs of the people. I am a helper of the

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. L3N1348-1🕒	1.00	“⏎”“<\|im_end\|>”“␍⏎”
2. L1N1970+1💥	0.99	“<\|im_end\|>”“⏎”“ ⏎”
3. L3N2832-1🕒	0.99	“⏎”“<\|im_end\|>”“⏎ ⏎”
4. L2N8726-1🕒	0.99	“<\|im_end\|>”“⏎”“⏎ ⏎”
5. L2N5696+1🕒	0.99	“<\|im_end\|>”“⏎”“?\”
6. L2N5409+1🕒	0.99	“<\|im_end\|>”“⏎”“\n”
7. L11N1543-1🕒	0.99	“<\|im_end\|>”“⏎”“ ⏎”
8. L3N6461+1🕒	0.99	“<\|im_end\|>”“⏎”“\n”
9. L2N9159+1🕒	0.99	“<\|im_end\|>”“⏎”“?\”
10. L6N5934+1💤	0.99	“⏎”“<\|im_end\|>”“⏎ ⏎”

Shadow specimen, apart from the ten: L2N5788+1💥, -0.19.

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 2, neuron 5788, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.73, 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
L2N5788+1💥 shadow specimen t0-v0.1	3.767	0.28	4.307	2.90	“<\|im_end\|>”“ image”“ imagery”“ representation”“ persona”“ images”“形象”“ depiction”
L2N5788-1 t0-v0.1	1.726	0.49	2.082	1.94	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.