Layer 18 · Neuron 4541 · suppressed

L18N4541-1

Word quirks:

“ here”“ ‘”“here”“ Here”“ ’”“ another”“这儿”“此处”

💤 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, an AI model developed by Tongyi Lab. My mission is to empower users by providing high-quality assistance across a wide range of tasks. Here's a breakdown of my capabilities and purpose:

Human-Centric Support: I aim to help users solve problems, create content, analyze data, and explore ideas through natural language interactions. Whether you need coding help, creative writing, or technical support, I strive to deliver accurate and context-aware responses.

Cross-Scenario Utility: From debugging code for developers to summarizing documents for business professionals, I adapt to diverse

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. L19N4017+1🕒	0.92	“ here”“ HERE”“ Here”
2. L20N1944+1🕒	0.91	“ here”“ Here”“这里”
3. L31N723-1💥	0.91	“ here”“这里”“here”
4. L20N2865+1🕒	0.91	“ here”“ Here”“Here”
5. L29N5171-1🕒	0.90	“这里的”“ here”“here”
6. L18N6256-1🕒	0.90	“ here”“here”“在这里”
7. L22N2214+1🕒	0.90	“ here”“这里”“ Here”
8. L22N4380+1🕒	0.90	“ here”“这里”“ Here”
9. L21N8896-1🕒	0.90	“ here”“这里”“在这里”
10. L22N3518+1🕒	0.90	“ here”“这里”“here”

Shadow specimen, apart from the ten: L18N4541+1🕒, -0.15.

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 18, neuron 4541, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.36, top-1 agreement 0.72) 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
L18N4541+1🕒 shadow specimen t0-v0.1	1.610	0.47	1.954	1.97	“ tempered”“ validated”“ manifested”“ into”“让它们”“ consolidated”“ filtered”“ checked”
L18N4541-1 t0-v0.1	0.355	0.72	0.479	1.05	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.