Layer 30 · Neuron 5618 · suppressed

L30N5618-1

Word quirks:

“ement”“ure”“al”“ice”“val”“lement”“alh”“ion”

🕒 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 **Qalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalalal

The AI judge wasn't sure this holds together.

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. L19N519-1💤	0.73	“al”“ic”“e”
2. L5N4166-1💥	0.71	“e”“ely”“ie”
3. L4N4966-1🕒	0.70	“i”“e”“ure”
4. L5N7183+1💥	0.69	“ator”“ial”“ital”
5. L30N1519-1💤	0.68	“al”“el”“ar”
6. L31N3772-1💥	0.68	“al”“el”“il”
7. L10N2074+1🕒	0.68	“ire”“ion”“ure”
8. L5N4878-1💤	0.67	“ation”“ity”“al”
9. L7N4165-1💤	0.67	“ess”“ient”“ine”
10. L5N6163+1💥	0.67	“e”“er”“el”

Shadow specimen, apart from the ten: L30N5618+1💤, 0.33.

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 30, neuron 5618, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.54, top-1 agreement 0.77) 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
L30N5618+1💤 shadow specimen t0-v0.1	0.344	0.80	0.378	1.50	“INGER”“rams”“orna”“osság”“ities”“ating”“性强”“gen”
L30N5618-1 t0-v0.1	0.537	0.77	0.626	1.59	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.