Layer 12 · Neuron 2373 · boosted

L12N2373+1

Word quirks:

“ ——”“ —”“ –”“ ***”“ --”“ ****”“ ---”“ <U+00A0>”

💤 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 Qwen3.5, a large language model developed by Alibaba Cloud. My mission is to assist users in various tasks, from creative writing to complex problem-solving and data analysis. I aim to provide high-quality support across different domains, including education, healthcare, and more. 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. L13N6205-1💤	0.95	“ —”“ ——”“ ***”
2. L12N742+1🕒	0.95	“ --”“ ---”“ —”
3. L12N171+1💤	0.95	“ ***”“ --”“ –”
4. L10N556-1💤	0.93	“ ——”“ \"”“ --”
5. L11N2635+1🕒	0.93	“ ⏎”“ —”“ ——”
6. L16N4121+1🕒	0.93	“ --”“ —”“ ---”
7. L12N6903+1🕒	0.92	“ --”“ —”“ –”
8. L13N1460-1💤	0.91	“ ——”“ --”“ ---”
9. L16N4037+1🕒	0.91	“ —”“ --”“ –”
10. L12N3671-1💤	0.91	“ --”“<\|im_end\|>”“⏎”

Shadow specimen, apart from the ten: L12N2373-1💤, 0.13.

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 12, neuron 2373, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.61, top-1 agreement 0.67) 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
L12N2373+1 t0-v0.1	0.609	0.67	0.796	1.12	Top boosted tokens ↑
L12N2373-1💤 shadow specimen t0-v0.1	0.662	0.69	0.931	1.29	“ referenced”“ described”“ related”“ remembered”“⏎”“ discussed”“ ⏎”“ clearer”

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.