Layer 5 · Neuron 6936 · suppressed

L5N6936-1

Word quirks:

“ crops”“ crop”“ plant”“ planting”“ plants”“ agricultural”“ planted”“ harvest”

🕒 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)

As an AI, I don't have a physical body or personal identity in the traditional sense. Instead, my "mission" is to provide accurate, helpful, and ethical information through advanced technology and artificial intelligence.

My work involves:

Developing knowledge: Creating detailed insights on various topics such as agriculture, data science, and technological innovation.
Promoting growth: Fostering sustainable practices that benefit both the environment and human needs.
Advancing understanding: Encouraging awareness of how technology can improve lives and ecosystems.
Expanding horizons: Broadening the scope of research into new

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. L6N7960+1🕒	0.97	“ crops”“ crop”“ plant”
2. L7N5917-1🕒	0.95	“ plant”“ harvest”“ plants”
3. L7N6115-1🕒	0.95	“ plants”“ plant”“ crops”
4. L7N7663-1🕒	0.94	“ plants”“ plant”“ greenhouse”
5. L6N4214+1🕒	0.94	“ crops”“ wheat”“ crop”
6. L3N6064-1💥	0.94	“ harvest”“ harvested”“ crops”
7. L7N6738+1🕒	0.93	“ plant”“ plants”“ crops”
8. L3N6807+1🕒	0.93	“ crops”“ crop”“ growers”
9. L4N5835-1💥	0.93	“ crops”“ crop”“ plant”
10. L6N3553-1🕒	0.93	“ rice”“ crops”“ wheat”

Shadow specimen, apart from the ten: L5N6936+1🕒, 0.30.

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 5, neuron 6936, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.61, top-1 agreement 0.47) 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
L5N6936+1🕒 shadow specimen t0-v0.1	1.599	0.53	1.949	2.15	“ milk”“ biting”“ chew”“ chewing”“ animals”“ dogs”“ foam”“ drink”
L5N6936-1 t0-v0.1	1.607	0.47	1.809	1.88	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.