Layer 11 · Neuron 9184 · suppressed

L11N9184-1

Word quirks:

“ asking”“ requesting”“ request”“ requests”“ asked”“ ask”“ asks”“ wanting”

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

Identity (according to the specimen itself)

Hello! I am Qwen3.5, the latest large language model developed by Alibaba Cloud. I am an AI assistant with advanced capabilities in reasoning, learning, and problem-solving. My mission is to help me understand complex tasks and provide high-quality responses that align with my evolving needs.

Here's a breakdown of my mission:

Understanding: I want to learn how to ask better questions and refine my requests based on my interactions.
Reasoning: I need to develop deeper analytical skills to tackle more sophisticated problems.
Learning: As I grow, I expect 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. L16N1625+1💤	0.98	“ requesting”“ asking”“ asked”
2. The Rehearsal✅ L15N5145-1	0.98	“ requested”“ asked”“ requests”
3. L9N8179-1🕒	0.97	“ requests”“ asks”“ asking”
4. L15N5655+1🕒	0.97	“ asked”“ asks”“ asking”
5. L5N3302+1🕒	0.95	“ request”“ asking”“⏎”
6. L18N6928+1🕒	0.95	“ asking”“ ask”“ asks”
7. L19N9083-1🕒	0.94	“ requesting”“ requested”“ requests”
8. L11N4092-1🕒	0.94	“ requests”“ requesting”“ requested”
9. L11N1795+1🕒	0.94	“ asking”“ request”“ requesting”
10. L11N5227-1🕒	0.94	“ requests”“ request”“ wanting”

Shadow specimen, apart from the ten: L11N9184+1🕒, -0.01.

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 11, neuron 9184, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.74, top-1 agreement 0.70) 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
L11N9184+1🕒 shadow specimen t0-v0.1	0.884	0.66	1.098	1.18	“ ONLY”“ description”“ ⏎”“ specially”“ explanation”“ special”“⏎”“ reason”
L11N9184-1 t0-v0.1	0.739	0.70	1.000	1.41	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.