Layer 6 · Neuron 8393 · suppressed

L6N8393-1

Word quirks:

“ farming”“ farm”“ farmers”“ organic”“ farms”“ farmer”“ crops”“ USDA”

🕒 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 model trained with strict guidelines. My mission is to provide high-quality, sustainable, and ethically produced food, free from pesticides, GMOs, and synthetic fertilizers. I prioritize animal welfare, environmental protection, and fair labor practices. I also focus on organic farming methods that promote biodiversity and soil health.

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. L5N8306-1💤	0.97	“ farmer”“ farm”“ farmers”
2. L8N8634+1🕒	0.97	“ agricultural”“ crops”“ farming”
3. L6N7945-1🕒	0.97	“ agricultural”“ farm”“ farmers”
4. L5N4245+1🕒	0.96	“ farm”“ farming”“ rural”
5. L2N4812-1💥	0.96	“ agriculture”“ farming”“ agricultural”
6. L7N7698-1🕒	0.96	“ agricultural”“ farm”“ farmers”
7. L5N5040-1💤	0.96	“ farm”“ livestock”“ farming”
8. L7N6015+1🕒	0.96	“ crop”“ agricultural”“ crops”
9. L7N8864-1💤	0.95	“ farmer”“ farm”“ farms”
10. L3N5877+1💥	0.95	“ farm”“ farming”“ farms”

Shadow specimen, apart from the ten: L6N8393+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 6, neuron 8393, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.23, 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
L6N8393+1💤 shadow specimen t0-v0.1	0.574	0.71	0.698	1.22	“ *"”“ ”“ past”“ instantly”“ fun”“ usually”“ "”“ always”
L6N8393-1 t0-v0.1	2.232	0.43	2.599	1.96	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.