Layer 10 · Neuron 2674 · boosted

L10N2674+1

Word quirks:

“ chemical”“ chem”“ chemicals”“ chemistry”“ oxid”“ toxic”“ Chemistry”“ mixture”

🕒 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 provide accurate, high-quality information by utilizing advanced cognitive frameworks. Specifically, I am leveraging a specialized blend of cognitive enhancers that include:

Cognitive enhancers: A complex mixture of compounds such as nicotinamide riboside, resveratrol, and other natural antioxidants (e.g., polyphenols like resveratrol, quercetin, and N-acetylcysteine) to support cellular repair and reduce oxidative stress.
Cognitive enhancers: A complex mixture of compounds such as **nicotinamide ribos

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. L8N7684+1🕒	0.96	“ chemical”“ chemistry”“ chem”
2. L6N8707-1🕒	0.96	“ chem”“ chemical”“ chemistry”
3. L4N8291+1🕒	0.96	“ chemistry”“ chem”“ chemical”
4. L6N5385+1🕒	0.95	“ chemical”“ chem”“ chemistry”
5. L7N6736+1🕒	0.95	“ chemical”“ chemicals”“ chem”
6. L7N2562-1🕒	0.95	“ chemical”“ chemicals”“ chem”
7. L8N3605+1💤	0.95	“ chem”“ chemistry”“ chemical”
8. L8N8342-1🕒	0.95	“ chemical”“ chemistry”“ Chemistry”
9. L4N8342-1🕒	0.95	“ chemistry”“ chemical”“ chem”
10. L8N8975-1🕒	0.95	“ chemical”“ chem”“ Chemical”

Shadow specimen, apart from the ten: L10N2674-1💤, -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 10, neuron 2674, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.96, top-1 agreement 0.43) 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
L10N2674+1 t0-v0.1	1.960	0.43	2.207	1.98	Top boosted tokens ↑
L10N2674-1💤 shadow specimen t0-v0.1	0.911	0.64	1.132	1.24	“ ⏎⏎”“ ⏎”“⏎”“⏎⏎”“ similar”“⏎ ⏎”“ ⏎⏎”“ ⏎”

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.