Layer 20 · Neuron 6751 · boosted

L20N6751+1

Word quirks:

“ referring”“ meaning”“ mean”“ means”“ Mean”“ meant”“ Meaning”“指的”

💤 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-6.5, the latest version of the Qwen series (the "new version" of the 6th iteration), developed by Tongyi NLP. As a large language model, my primary mission is to help users achieve their goals by providing high-quality assistance across diverse domains.

What I Mean by My Mission:

Understanding & Clarity: I aim to grasp complex information (whether text, data, or multimodal content) and communicate it clearly, whether in a conversation, report, or code.
Actionable Support: Whether you need

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. L19N8683-1💤	0.95	“ meaning”“ means”“ Means”
2. L17N6240+1🕒	0.94	“ meaning”“ means”“意味着”
3. L27N2722+1🕒	0.94	“ means”“means”“ meaning”
4. L23N4142-1🕒	0.94	“ meaning”“ means”“ Meaning”
5. L20N5476+1💤	0.93	“意味着”“ means”“ Means”
6. L21N1704+1🕒	0.93	“ means”“意味着”“这意味着”
7. L20N7410-1🕒	0.93	“ mean”“的意思”“ meaning”
8. L17N7918-1🕒	0.93	“ meaning”“meaning”“意指”
9. L25N2278-1🕒	0.92	“ means”“ Means”“意味着”
10. L20N1067-1🕒	0.92	“ means”“这意味着”“意味着”

Shadow specimen, apart from the ten: L20N6751-1🕒, -0.06.

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 20, neuron 6751, 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
L20N6751+1 t0-v0.1	0.631	0.68	0.761	1.21	Top boosted tokens ↑
L20N6751-1🕒 shadow specimen t0-v0.1	0.700	0.68	0.808	1.42	“ commander”“ president”“ scientist”“ Positions”“ researcher”“ Scientist”“ chairman”“ superintendent”

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.