Layer 13 · Neuron 2763 · boosted

L13N2763+1

Word quirks:

“ ANY”“ any”“ anywhere”“ anyone”“ whenever”“any”“ EVERY”“ Any”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

Hello! I am Qwen, a large language model developed by Tongyi Lab. My mission is to empower users with knowledge and capabilities through cutting-edge technology, ensuring that AI serves humanity effectively and safely.

If you have any questions or need assistance, feel free to ask! 😊
</think>

I am Qwen, a large language model designed to help users efficiently. Here's a quick overview of my capabilities:

🌐 What I Am (Qwen)

Qwen3.0 (the latest version) is part of the Tongyi Lab family, which includes models

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. L18N4348+1🕒	0.97	“ any”“ anywhere”“ ANY”
2. L10N8690-1🕒	0.96	“ any”“ ANY”“ anytime”
3. L21N8352+1💥	0.96	“ anytime”“ any”“ anywhere”
4. L15N7958-1🕒	0.96	“ any”“ anywhere”“ ANY”
5. L20N933-1🕒	0.95	“ every”“ any”“ each”
6. L14N7808+1🕒	0.95	“ any”“ anywhere”“ ANY”
7. L16N5836+1🕒	0.94	“ any”“ anywhere”“ anyone”
8. L17N8388+1🕒	0.94	“ any”“ wherever”“ anywhere”
9. L16N8104+1🕒	0.94	“ any”“ anything”“ anywhere”
10. L14N7793+1🕒	0.94	“ any”“ ANY”“ anywhere”

Shadow specimen, apart from the ten: L13N2763-1🕒, -0.10.

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 13, neuron 2763, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.91, 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
L13N2763+1 t0-v0.1	0.905	0.66	1.043	1.00	Top boosted tokens ↑
L13N2763-1🕒 shadow specimen t0-v0.1	1.051	0.59	1.315	1.51	“ (”“ higher”“ "”“ markedly”“ "”“ *”“<\|im_end\|>”“ "'”

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.