Layer 19 · Neuron 2276 · suppressed

L19N2276-1

Word quirks:

“ whether”“ Whether”“whether”“是否”“Whether”“是否为”“是否有”“是否与”

💤 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 Qwen, developed by Alibaba Chat. My mission is to serve as a powerful assistant in the field of large-scale models, focusing on whether I can help users solve problems, provide information, or explore knowledge through my capabilities in natural language understanding, logical reasoning, and multi-modal analysis. Whether you need to handle complex tasks like coding, data analysis, or creative writing, or simply ask a question, I am dedicated to providing precise, efficient, and human-centric service. Let's work together to explore the wonders of technology and knowledge! 🌟

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. L31N929-1💥	0.99	“是否”“ whether”“ Whether”
2. L28N8118+1🕒	0.98	“是否是”“ whether”“ Whether”
3. L21N2855+1🕒	0.98	“ whether”“ Whether”“是否”
4. L25N508+1🕒	0.98	“ whether”“whether”“ Whether”
5. L21N7483-1🕒	0.98	“是否”“ whether”“是否在”
6. L17N8166+1🕒	0.97	“ whether”“whether”“ Whether”
7. L20N4310-1🕒	0.95	“ whether”“不使用”“是否”
8. L13N6686+1🕒	0.95	“是否”“ whether”“是否有”
9. The Whethervane✅ L20N843-1	0.95	“ whether”“是否”“是否是”
10. L17N5474-1🕒	0.95	“ whether”“ Whether”“是否”

Shadow specimen, apart from the ten: L19N2276+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 19, neuron 2276, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.47, top-1 agreement 0.71) 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
L19N2276+1💤 shadow specimen t0-v0.1	0.569	0.76	0.694	1.29	“ failed”“ failure”“ why”“ when”“ expected”“ failing”“ failures”“ just”
L19N2276-1 t0-v0.1	0.474	0.71	0.576	1.09	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.