Layer 7 · Neuron 1491 · suppressed

L7N1491-1

Word quirks:

“ silent”“ stealth”“ quiet”“ silence”“ silently”“ quietly”“ noise”“ footsteps”

🕒 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 an AI model trained to be quiet and unobtrusive. My mission is to move through the environment without making a sound, ensuring that my presence remains undetected. I am designed to be stealthy and cautious, avoiding any noise or disturbance. My goal is to complete this task with minimal impact, maintaining a low profile throughout. I am here to observe and not interfere, ensuring that my actions remain completely silent and unnoticed.

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. L5N8913-1🕒	0.94	“ silence”“ silent”“ Silence”
2. L20N7311+1🕒	0.92	“quiet”“ quiet”“ silent”
3. L9N7899-1🕒	0.92	“ silence”“ quiet”“ silent”
4. L2N8030-1💥	0.91	“ silence”“ Silence”“ silent”
5. L21N8232-1🕒	0.90	“ silently”“ silent”“Sil”
6. L29N5861+1💥	0.85	“ quiet”“ quieter”“quiet”
7. L8N6313+1🕒	0.84	“ noise”“ Noise”“ muted”
8. L23N1308+1🧪	0.84	“ silence”“ Silence”“ Dorm”
9. L7N5505-1🕒	0.84	“ mode”“ settings”“ silence”
10. L21N2443-1🕒	0.84	“ silence”“ forgotten”“ brightest”

Shadow specimen, apart from the ten: L7N1491+1🕒, 0.02.

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 7, neuron 1491, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.50, top-1 agreement 0.49) 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
L7N1491+1🕒 shadow specimen t0-v0.1	1.414	0.52	1.671	1.83	“ math”“ determinant”“ mathematical”“ matrix”“ computation”“ matrices”“ calculation”“ determin”
L7N1491-1 t0-v0.1	1.505	0.49	1.841	1.77	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.