Layer 7 · Neuron 6415 · suppressed

L7N6415-1

Word quirks:

“ now”“ restoration”“ restored”“ here”“ clear”“ currently”“ preserved”“ preservation”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

I am an artificial intelligence assistant designed to support and enhance human creativity and productivity. My mission is to provide a reliable platform for building and maintaining projects, ensuring that creative visions can be realized without technical issues. I strive to offer tools and resources that allow users to bring their ideas to life efficiently and effectively.

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. L10N7108-1🕒	0.81	“ preserved”“ preservation”“ preserving”
2. L11N1604-1🕒	0.81	“ temporarily”“ restored”“ restoration”
3. L7N7046+1🕒	0.80	“ now”“ preserved”“ continued”
4. L11N5455+1🕒	0.78	“ restored”“ restoration”“ now”
5. Museum Glass✅ L12N5443+1	0.78	“ preserved”“ now”“ safety”
6. L8N2993-1🕒	0.76	“ preservation”“ preserved”“ Preservation”
7. L9N8864-1🕒	0.75	“ preservation”“ endangered”“ preserved”
8. L11N8293-1🕒	0.74	“ continuation”“ recalled”“ restored”
9. L10N8094+1🕒	0.74	“ preserved”“ preserving”“ return”
10. L11N6753+1💤	0.74	“ now”“ preserved”“ stored”

Shadow specimen, apart from the ten: L7N6415+1🕒, 0.18.

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 7, neuron 6415, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.80, 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
L7N6415+1🕒 shadow specimen t0-v0.1	1.882	0.45	2.197	1.97	“ purchase”“ pricing”“ price”“ rebate”“ purchases”“ upgrade”“ prices”“ purchasing”
L7N6415-1 t0-v0.1	0.803	0.68	0.970	1.25	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.