Layer 9 · Neuron 9011 · boosted

L9N9011+1

Word quirks:

“ info”“ restricted”“ sensitive”“ privacy”“ secret”“ hidden”“ private”“ secrecy”

💤 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 Qwen3.5, a large language model trained by Alibaba Cloud. My mission is to provide helpful, accurate information on a wide range of topics. I do not have a personal identity or specific purpose beyond my programming. I am designed to be versatile and can adapt to different contexts as needed.

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. The Secret-Keeper✅ L5N5305-1	0.87	“ privacy”“ concealed”“ secrecy”
2. L13N7223+1🕒	0.85	“ secret”“ hidden”“ internal”
3. L9N7069-1🕒	0.84	“ sensitive”“ privacy”“ confidentiality”
4. L8N6783-1🕒	0.82	“ confidential”“ privacy”“ protected”
5. L9N1454+1🕒	0.81	“ private”“ privacy”“ secluded”
6. L16N4844+1🕒	0.81	“ privacy”“隐私”“ secrecy”
7. L11N2982+1🕒	0.81	“ privacy”“ Privacy”“隐私”
8. L7N3654-1🕒	0.80	“ privately”“ private”“ internal”
9. L5N6872-1🕒	0.80	“ confidential”“ secret”“ quietly”
10. L8N5526+1🕒	0.79	“ confidentiality”“ secrecy”“ confidential”

Shadow specimen, apart from the ten: L9N9011-1🕒, -0.13.

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 9, neuron 9011, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.88, top-1 agreement 0.64) 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
L9N9011+1 t0-v0.1	0.883	0.64	1.228	1.54	Top boosted tokens ↑
L9N9011-1🕒 shadow specimen t0-v0.1	1.436	0.56	1.609	1.49	“ “”“ "”“ concern”“ *“”“ ””“ ‘”“ ⏎”“”:”

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.