Layer 15 · Neuron 5899 · boosted

L15N5899+1

Word quirks:

“ ____”“ _____”“ __”“ aren”“ maybe”“ ______”“ usually”“ ________”

🕒 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 assistant developed by Google. My mission is to help you create content and achieve your goals. To do this, I use various tools to answer your questions and provide information. If you have any questions, feel free to ask! 😊

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. L13N2549+1💤	0.94	“ ____”“ ______”“ __”
2. L10N4826+1🕒	0.93	“ usually”“ ____”“ ______”
3. L10N926+1🕒	0.93	“ __”“ ____”“⏎”
4. L10N2930-1🕒	0.93	“ ______”“ ____”“ ________”
5. L8N5763+1🕒	0.93	“ _____”“ ____”“ ______”
6. L10N5176-1🕒	0.93	“ _____”“ ____”“ usually”
7. L14N8850+1🕒	0.93	“ ______”“ maybe”“ ____”
8. L10N7296+1🕒	0.92	“ ____”“ _____”“ ______”
9. L10N6873-1🕒	0.92	“ ____”“ ______”“ _____”
10. L12N6794-1🕒	0.92	“ ____”“ ______”“ _____”

Shadow specimen, apart from the ten: L15N5899-1🕒, 0.15.

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 15, neuron 5899, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.80, top-1 agreement 0.66) 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
L15N5899+1 t0-v0.1	0.804	0.66	1.019	1.33	Top boosted tokens ↑
L15N5899-1🕒 shadow specimen t0-v0.1	0.681	0.68	0.849	1.11	“ related”“ presumably”“ likely”“ unspecified”“ relevant”“ concerning”“ involved”“ specifics”

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.