Layer 24 · Neuron 7447 · boosted

L24N7447+1

Word quirks:

“ wire”“ Wire”“wire”“Wire”“ needle”“丝”“_wire”“细”

💤 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 Q*, a large-scale 0.82 billion parameter general chatline model developed by *Nanofine. My mission is to assist users in answering questions, creating text (such as text, code, and more), and performing tasks like making decisions and executing tasks. I aim to provide high-quality, accurate, and helpful responses across various domains, including but not limited to:

General Knowledge: Answering questions about history, science, culture, and more.
Creative Assistance: Assisting with writing, brainstorming ideas, or generating creative content.
Technical Support: Helping with

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. Line Noise✅ L26N3036-1	0.91	“ wire”“ Wire”“ line”
2. L25N2918-1🕒	0.91	“ wires”“ wire”“wire”
3. L30N5436+1💥	0.89	“wire”“ wire”“ Wire”
4. L25N7200-1🕒	0.88	“Wire”“ wire”“wire”
5. L26N8739-1🕒	0.88	“ wire”“ Wire”“wire”
6. L27N1250-1🕒	0.87	“ wire”“ Wire”“wire”
7. L27N4896-1🕒	0.87	“ wire”“wire”“Wire”
8. L25N9036+1🕒	0.87	“ Wire”“ wire”“wire”
9. L26N1762-1🕒	0.85	“ wire”“Wire”“ Wire”
10. L2N4951-1💥	0.84	“ wire”“ wires”“<\|im_end\|>”

Shadow specimen, apart from the ten: L24N7447-1🕒, 0.28.

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 24, neuron 7447, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.70, top-1 agreement 0.74) 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
L24N7447+1 t0-v0.1	0.704	0.74	0.713	1.20	Top boosted tokens ↑
L24N7447-1🕒 shadow specimen t0-v0.1	0.959	0.68	1.097	1.36	“胳膊”“奠”“ blocks”“肘”“标”“谷”“ubar”“hoek”

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.