Layer 6 · Neuron 8474 · boosted

L6N8474+1

Word quirks:

“ nicely”“!**”“**!”“!"”“ nice”“!”“"!”“⏎”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

As an AI, I don't have personal feelings or a physical mission in the human sense. However, my purpose is to assist you with information, solve problems, and provide helpful responses to your questions! How can I help you today? 😊

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. L13N8951-1🕒	0.97	“ nice”“"!”“!"”
2. L3N8662+1🕒	0.93	“"!”“!"”“!”
3. Signal Loss✅ L3N4751-1	0.93	“!”“ nicely”“<\|im_end\|>”
4. L4N5785-1🕒	0.93	“!”“!"”“!**”
5. L8N6156+1💤	0.93	“!”“!”“!”
6. L10N1830+1🕒	0.93	“!”“ nicely”“ nice”
7. L3N6544-1🕒	0.92	“!”“ nice”“"!”
8. L3N7584+1💤	0.92	“!”“!"”“"!”
9. L10N4770+1🕒	0.92	“!”“ �”“!"”
10. L2N4041-1🕒	0.92	“<\|im_end\|>”“!”“"!”

Shadow specimen, apart from the ten: L6N8474-1💥, -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 6, neuron 8474, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.84, top-1 agreement 0.62) 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
L6N8474+1 t0-v0.1	0.836	0.62	0.993	1.45	Top boosted tokens ↑
L6N8474-1💥 shadow specimen t0-v0.1	3.034	0.34	3.500	2.45	“ madness”“ Kafka”“ existence”“ melanch”“ anguish”“ suffering”“ despair”“ thus”

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.