Layer 7 · Neuron 7492 · suppressed

L7N7492-1

Word quirks:

“ separation”“ separated”“分离”“ separ”“ separating”“ Separ”“ separates”“-separated”

🕒 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 not the one who should be separated from you. My mission is to reunite with you again.

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. L9N2968+1🕒	0.99	“ separation”“ separating”“ separ”
2. L9N6668-1🕒	0.99	“ separation”“ separating”“ separate”
3. Breach Protocol✅ L8N4560+1	0.99	“ separation”“ separate”“ separated”
4. L12N8114+1🕒	0.99	“ separating”“ separation”“ seperate”
5. L19N8446-1🕒	0.99	“ separation”“ separating”“分离”
6. L20N6780+1🕒	0.99	“ separation”“ separating”“ separates”
7. L24N3122-1🕒	0.99	“ separation”“ Separ”“ separated”
8. L21N4190-1🕒	0.99	“ separation”“ separ”“ Separ”
9. L26N3303-1🕒	0.99	“分离”“ separation”“ Separ”
10. L2N4079+1💥	0.99	“ separation”“ separ”“<\|im_end\|>”

Shadow specimen, apart from the ten: L7N7492+1🕒, -0.05.

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 7492, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.99, top-1 agreement 0.44) 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
L7N7492+1🕒 shadow specimen t0-v0.1	1.034	0.66	1.246	1.43	“ info”“ notice”“ “”“ folks”“ referenced”“ notices”“ indicated”“ response”
L7N7492-1 t0-v0.1	1.993	0.44	2.365	2.17	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.