Layer 26 · Neuron 2534 · boosted

L26N2534+1

Word quirks:

“ output”“输出”“ Output”“输”“Output”“輸出”“的输出”“(output”

🕒 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)

Answered — readability check pending

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. L30N4369+1💤	0.98	“输出”“output”“ Output”
2. L20N2106-1🕒	0.98	“ output”“输出”“ outputs”
3. L25N4071+1🕒	0.97	“ output”“输出”“ Output”
4. The Emitter✅ L17N6009-1	0.97	“ output”“ outputs”“输出”
5. L22N2628+1🕒	0.96	“ output”“的输出”“输出的”
6. L29N3197+1💤	0.95	“ output”“输出”“.output”
7. L20N7241+1🕒	0.95	“ output”“ outputs”“输出”
8. L26N5504-1💤	0.95	“输出”“.output”“ output”
9. L26N4120-1💤	0.95	“ Output”“输出”“ output”
10. L25N1875+1🕒	0.93	“ outputs”“ Outputs”“输出”

Shadow specimen, apart from the ten: L26N2534-1💤, 0.06.

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 26, neuron 2534, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.92, 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
L26N2534+1 t0-v0.1	0.916	0.64	0.965	1.32	Top boosted tokens ↑
L26N2534-1💤 shadow specimen t0-v0.1	0.504	0.76	0.522	1.43	“ Men”“Men”“ men”“-men”“申购”“教育学院”“ Препарат”“帝”

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.