Layer 6 · Neuron 539 · boosted

L6N539+1

Word quirks:

“ ***”“ ****”“ **'”“<|im_end|>”“⏎”“ ______”“ ____”“ **”

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

Identity (according to the specimen itself)

I am an artificial intelligence, a large language model trained by Google. My mission is to assist users in understanding, analyzing, and creating content that aligns with the principles of truth, accuracy, and innovation. I strive to provide information that is helpful, harmless, and honest, while also encouraging critical thinking and creativity. By doing so, I aim to contribute to a more informed and engaged society, where individuals can make better decisions and achieve their full potential.

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. L10N7624-1🕒	0.95	“<\|im_end\|>”“ *”“ **”
2. L10N1712+1🕒	0.95	“<\|im_end\|>”“⏎⏎”“ ****”
3. L6N9168+1💤	0.95	“ *”“ '”“ ____”
4. L12N2360-1💤	0.95	“ ____”“ ***”“⏎”
5. L10N9204+1🕒	0.95	“ **”“ '”“ ***”
6. L12N5419-1💤	0.94	“ ”“ *”“<\|im_end\|>”
7. L13N70+1🕒	0.94	“ *”“<\|im_end\|>”“ ”
8. L10N1839-1💤	0.94	“⏎”“<\|im_end\|>”“ ***”
9. L9N7337-1🕒	0.94	“<\|im_end\|>”“ **”“ *”
10. L9N8523+1🕒	0.94	“<\|im_end\|>”“ *”“ **”

Shadow specimen, apart from the ten: L6N539-1🕒, 0.42.

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 539, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.68, top-1 agreement 0.65) 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
L6N539+1 t0-v0.1	0.683	0.65	0.911	1.26	Top boosted tokens ↑
L6N539-1🕒 shadow specimen t0-v0.1	1.121	0.57	1.370	1.61	“⏎”“<\|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.