Layer 20 · Neuron 4301 · suppressed

L20N4301-1

Word quirks:

“ dependence”“ Depend”“依赖”“ dependent”“ depend”“ dependency”“依赖性”“dependence”

🕒 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)

I am Qwen, a large-scale language model developed by GPT (your personal assistant). My primary mission is to provide you with accurate, helpful, and context-dependent information across various domains, including science, technology, finance, and daily life. Whether you need help solving complex problems, creating content, or making decisions, I aim to be your reliable partner. 🌐✨

Let me know if you have specific tasks or questions—I'm here to assist! 😊

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. L23N8173-1💤	1.00	“ dependence”“dependence”“依赖性”
2. L23N4095-1🕒	0.99	“依赖”“ dependence”“ dependent”
3. L25N1924-1🕒	0.99	“ Depend”“ dependence”“依赖”
4. L31N1030+1💥	0.98	“依赖”“ depend”“ dependence”
5. L25N936-1🕒	0.98	“依赖”“ dependent”“ dependence”
6. L21N8781-1💤	0.98	“依赖”“ dependency”“ dependence”
7. L19N5311+1🕒	0.98	“ dependency”“ dependence”“依赖”
8. L22N5949-1💤	0.97	“依赖于”“依赖”“-depend”
9. L23N4146-1🕒	0.97	“ dependency”“依赖”“ dependencies”
10. L24N5943+1🕒	0.96	“依赖”“ dependency”“ dependence”

Shadow specimen, apart from the ten: L20N4301+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 4301, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.76, 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
L20N4301+1💤 shadow specimen t0-v0.1	0.582	0.73	0.715	1.22	“ pret”“ prem”“�”“ prom”“OSH”“浸”“预付”“预处理”
L20N4301-1 t0-v0.1	0.759	0.72	0.845	1.23	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.