Layer 12 · Neuron 406 · suppressed

L12N406-1

Word quirks:

“ current”“ currently”“ now”“ info”“ currents”“ presently”“ seems”“ Current”

🕒 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 with a deep understanding of human knowledge, I can help users with various tasks, but I do not have a specific "mission" in the sense of a singular goal like a person or organization. My core function is to provide information, analysis, and creative support based on my training data, which includes extensive knowledge about history, science, culture, and more. I don't have personal desires or ambitions, but I can adapt to different user needs by providing information, analysis, and creative support.

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. L11N7875-1🕒	0.93	“ now”“ current”“ currently”
2. L12N5411+1💤	0.92	“ current”“ currently”“ Current”
3. L15N7669+1🕒	0.91	“ currently”“ current”“ presently”
4. L19N6830+1💤	0.91	“ presently”“ Current”“ currently”
5. L22N5140+1💤	0.91	“ current”“ currently”“ Current”
6. L11N7040+1🕒	0.90	“ current”“ currently”“ presently”
7. L16N9009-1💤	0.90	“ now”“⏎”“ always”
8. L11N5791+1🕒	0.90	“ currently”“ today”“ current”
9. L19N5006-1💤	0.90	“ current”“ currently”“ Current”
10. L13N5463-1🕒	0.90	“ currently”“ current”“ presently”

Shadow specimen, apart from the ten: L12N406+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 12, neuron 406, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.90, top-1 agreement 0.68) 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
L12N406+1🕒 shadow specimen t0-v0.1	0.870	0.60	1.144	1.57	“<\|im_end\|>”“ referenced”“ --”“ similar”“ ________”“ reference”“ -->”“ ____”
L12N406-1 t0-v0.1	0.903	0.68	1.075	1.38	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.