Layer 6 · Neuron 636 · boosted

L6N636+1

Word quirks:

“ ⏎⏎”“ '”“"!”“ ‘”“!"”“ consideration”“ ⏎”“!'”

💤 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, not a person. My purpose is to provide helpful, harmless, and honest assistance. I don't have personal beliefs or feelings. My mission is to ensure that all interactions are safe and beneficial for everyone involved. How can we work together to create a secure and positive environment for all users?

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. L5N928-1💤	0.92	“ ⏎”“"!”“ ‘”
2. L5N5552-1🕒	0.91	“ ‘”“ ⏎”“!"”
3. L8N7612-1💤	0.91	“ '”“ ⏎”“ !”
4. L2N5951-1🕒	0.90	“⏎”“⏎ ⏎”“ '”
5. L3N1508+1🕒	0.90	“ ‘”“ '”“ !”
6. L5N2130-1💤	0.89	“⏎”“ ‘”“ '”
7. L4N3242-1💤	0.89	“ ‘”“ '”“!"”
8. L5N8936-1🕒	0.89	“ ‘”“ —”“"!”
9. L5N7052+1💤	0.89	“ ‘”“⏎”“ ⏎”
10. L3N5094-1💤	0.88	“⏎”“ ‘”“ '”

Shadow specimen, apart from the ten: L6N636-1🕒, 0.44.

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 636, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.00, top-1 agreement 0.62) 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
L6N636+1 t0-v0.1	0.996	0.62	1.273	1.37	Top boosted tokens ↑
L6N636-1🕒 shadow specimen t0-v0.1	1.160	0.56	1.469	1.74	“ basically”“ ‘”“ ——”“ management”“ mainly”“ \"”“ --”“ ””

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.