Layer 20 · Neuron 8928 · suppressed

L20N8928-1

Word quirks:

“ pressure”“ pressures”“pressure”“ Pressure”“Pressure”“压力”“-pressure”“ Push”

🕒 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 AI, a large language model created by Alibaba Cloud. My mission is to assist users in generating text, solving problems, and facilitating learning across various fields. I strive to provide accurate information, creative content, and helpful guidance while respecting user privacy and promoting positive values. Let me help you with what 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. L22N5713+1🕒	0.99	“ pressure”“ Pressure”“压力”
2. The Barometer✅ L7N3889-1	0.99	“ pressure”“ pressures”“ Pressure”
3. L2N3879+1💥	0.99	“ pressure”“ Pressure”“pressure”
4. L5N4812-1💥	0.98	“ pressure”“ pressures”“ Pressure”
5. L21N3671+1🕒	0.98	“ pressure”“ Pressure”“Pressure”
6. L6N7396+1🕒	0.98	“ pressure”“ pressures”“ Pressure”
7. L25N4723+1🕒	0.98	“ pressure”“ Pressure”“pressure”
8. L27N3748-1🕒	0.98	“ Pressure”“ pressure”“Pressure”
9. L20N4681+1🕒	0.98	“ pressure”“Pressure”“ pressures”
10. L24N8991+1🕒	0.98	“ Pressure”“ pressure”“压强”

Shadow specimen, apart from the ten: L20N8928+1🕒, 0.04.

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 8928, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.82, top-1 agreement 0.69) 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
L20N8928+1🕒 shadow specimen t0-v0.1	0.776	0.72	0.971	1.25	“ attaching”“附着”“ attach”“芒”“ovi”“adj”“attached”“ attaches”
L20N8928-1 t0-v0.1	0.822	0.69	0.905	1.28	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.