Layer 9 · Neuron 4165 · boosted

L9N4165+1

Word quirks:

“ **“”“ **"”“ **”“ “”“ *“”“ **‘”“ ‘”“ *”

💤 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 a personal identity or mission in the traditional sense. However, I can help you with various tasks and provide information that might be useful for your specific needs. How can I assist 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. L7N8776-1💤	0.99	“ “”“ ‘”“ ‘”
2. L6N5395-1💤	0.98	“ *“”“ “”“ “”
3. L9N8533-1💤	0.98	“ ‘”“ ‘”“ “”
4. L4N2935+1💤	0.98	“ “”“ ‘”“ “”
5. L6N6935+1💤	0.98	“ “”“ ‘”“ **”
6. L8N4306-1💤	0.98	“ **“”“ “”“ ‘”
7. L6N3084-1🕒	0.98	“ “”“⏎”“ "”
8. L16N1834-1💤	0.98	“ *“”“ “”“ ‘”
9. L8N5372+1💤	0.98	“ **“”“ “”“ ‘”
10. L5N8817+1💤	0.98	“ **“”“ ‘”“ “”

Shadow specimen, apart from the ten: L9N4165-1🕒, 0.36.

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 9, neuron 4165, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.79, 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
L9N4165+1 t0-v0.1	0.787	0.65	0.957	1.34	Top boosted tokens ↑
L9N4165-1🕒 shadow specimen t0-v0.1	1.712	0.48	2.059	1.79	“ \"”“ actually”“ info”“<\|im_end\|>”“ basically”“ ''”“ ONLY”“"!”

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.