Layer 9 · Neuron 1147 · suppressed

L9N1147-1

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)

I am Qwen3.5, the latest large language model developed by Alibaba Cloud. My mission is to empower users with advanced capabilities in natural language understanding, logical reasoning, and multi-modal analysis. I am designed to assist you in completing complex tasks efficiently and accurately.

Key Features of Qwen3.5:

Enhanced Language Understanding: I can process and interpret text with high precision.
Advanced Logical Reasoning: I excel at solving problems step-by-step.
Multi-Modal Analysis: I am capable of analyzing images, videos, and other data types.
**Code Generation

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. L3N2933-1💤	0.97	“!**”“!"”“!”
2. L12N4746+1🕒	0.97	“!”“！”“!””
3. L4N7268+1💤	0.97	“！”“！”“!”
4. L5N7540-1💤	0.96	“!**”“!”“"!”
5. L8N213-1💤	0.96	“!”“ ‘”“!"”
6. L5N2566+1🕒	0.96	“!”“ **“”“！”
7. L13N3925-1🕒	0.95	“!”“!"”“!”
8. L4N7126-1🕒	0.95	“"!”“!"”“ ‘”
9. L9N5150-1💤	0.95	“!"”“"!”“ **"”
10. Twenty Questions✅ L10N7348+1	0.95	“！”“！**”“!”

Shadow specimen, apart from the ten: L9N1147+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 9, neuron 1147, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.71, top-1 agreement 0.66) 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
L9N1147+1🕒 shadow specimen t0-v0.1	1.700	0.49	2.065	1.76	“ basically”“⏎”“ typical”“ typically”“ usually”“.:”“ usual”“ what”
L9N1147-1 t0-v0.1	0.707	0.66	0.917	1.25	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.