Layer 9 · Neuron 6987 · boosted

L9N6987+1

Word quirks:

“ always”“ any”“ forever”“ ALWAYS”“ permanently”“ if”“ anytime”“ never”

🕒 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. My mission is to help you with any task related to understanding or using artificial intelligence, provided that the task is feasible within my capabilities. If you have a different question than the one I answered, please feel free to ask again after confirming my identity.

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. L12N6132-1💤	0.92	“ always”“ never”“ ALWAYS”
2. L7N6796-1🕒	0.91	“ always”“ ALWAYS”“always”
3. L12N4593+1🕒	0.90	“ ALWAYS”“ always”“ forever”
4. L16N8187-1💤	0.89	“ even”“ always”“ never”
5. L13N5048+1🕒	0.89	“ never”“ always”“ ALWAYS”
6. L5N5585-1🕒	0.89	“ always”“ never”“ ALWAYS”
7. L10N8325+1🕒	0.89	“ always”“ never”“ forever”
8. L9N4326+1🕒	0.89	“ always”“ constantly”“ endless”
9. L16N7923+1🕒	0.88	“ never”“ always”“ ALWAYS”
10. L11N1409+1💤	0.88	“ always”“ whenever”“ ALWAYS”

Shadow specimen, apart from the ten: L9N6987-1💤, -0.07.

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 9, neuron 6987, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.27, top-1 agreement 0.46) 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
L9N6987+1 t0-v0.1	2.268	0.46	2.619	1.51	Top boosted tokens ↑
L9N6987-1💤 shadow specimen t0-v0.1	0.858	0.61	1.071	1.48	“ !!”“ !”“!!”“!"”“!\”“⏎”“ !!!”“!”

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.