Layer 21 · Neuron 6113 · boosted

L21N6113+1

Word quirks:

“犀牛”“ paw”“ racional”“ cub”“裘”“ Paw”“ Den”“雄鹿”

💤 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 QV, a large language model developed by Alibaba. My primary mission is to provide accurate, safe, and helpful assistance across a wide range of topics—from answering questions and solving problems to generating creative content and understanding human needs. I aim to be a reliable companion that helps users make informed decisions, enhance productivity, and explore ideas with confidence. How would you like to start? 🐇

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. Errata✅ L22N5044+0.6,L23N4769+0.6	0.75	“ paw”“毛”“胡须”
2. L23N7036+1💤	0.72	“ cobra”“ dragon”“牛的”
3. The Golden Retriever✅ L3N5161+0.48,L23N4769+0.64	0.72	“ paw”“ Paw”“爪”
4. Pawprint✅ L3N5161-0.48,L23N4769+0.64	0.71	“ paw”“ Paw”“爪”
5. The Stray✅ L4N8016+0.6,L23N4769+0.6	0.71	“ paw”“ Paw”“爪”
6. L23N4769+1🕒	0.71	“ paw”“ Paw”“爪”
7. L29N4671+1🕒	0.70	“蛇”“ bear”“鹰”
8. L30N7345+1💥	0.69	“熊”“狼”“ Fox”
9. The Eggcorn✅ L19N4699+0.6,L23N4769+0.6	0.68	“ paw”“ Paw”“爪子”
10. L24N3521+1💥	0.68	“类”“.rabbit”“涉”

Shadow specimen, apart from the ten: L21N6113-1🕒, 0.20.

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 21, neuron 6113, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.63, top-1 agreement 0.68) 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
L21N6113+1 t0-v0.1	0.630	0.68	0.755	1.23	Top boosted tokens ↑
L21N6113-1🕒 shadow specimen t0-v0.1	0.978	0.68	1.097	1.42	“rem”“uelas”“бла”“wel”“ recover”“$”“$_”“हत”

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.