Layer 10 · Neuron 7364 · suppressed

L10N7364-1

Word quirks:

“ rating”“ according”“ criteria”“ ratings”“ compatibility”“ description”“ preference”“ response”

💤 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 Tongyi Lab. My mission is to provide users with powerful, efficient, and intelligent capabilities that can handle complex tasks across various domains.

Key features include:

Advanced Language Understanding: The model excels at understanding and generating text in natural language, ensuring clear communication.
Logical Reasoning: Strong reasoning abilities allow the model to solve complex problems effectively.
Visual Analysis: High-quality image recognition helps in interpreting charts, diagrams, and other visual elements.
Multilingual Support: The model supports multiple languages, making it accessible to

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. The Autoresponder✅ L9N6092+1	0.72	“ rating”“ ratings”“ standard”
2. L8N3188+1🕒	0.72	“ rating”“ ratings”“ scale”
3. L9N4081-1🕒	0.71	“ rating”“ ratings”“ rated”
4. L9N7796-1🕒	0.71	“ rating”“ classification”“ rated”
5. L8N5833-1🕒	0.70	“ premium”“ benchmark”“ quality”
6. L3N7624+1🕒	0.70	“ rating”“ ratings”“ Rating”
7. L7N7548-1🕒	0.69	“ quality”“ rating”“ premium”
8. L6N6470-1💥	0.69	“ rating”“ age”“ content”
9. L6N1996+1🕒	0.69	“ rating”“ ratings”“ reviews”
10. L30N7904+1💥	0.68	“ rating”“ ratings”“ rated”

Shadow specimen, apart from the ten: L10N7364+1🕒, 0.21.

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 10, neuron 7364, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.93, 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
L10N7364+1🕒 shadow specimen t0-v0.1	1.074	0.64	1.356	1.36	“ usage”“⏎”“ normally”“ usually”“ used”“ use”“ mostly”“ users”
L10N7364-1 t0-v0.1	0.934	0.65	1.175	1.23	Top boosted tokens ↑

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.