Layer 6 · Neuron 5657 · suppressed

L6N5657-1

Word quirks:

“⏎”“ ⏎”“ —”“ _____”“ '”“⏎ ⏎”“ ⏎⏎”“!"”

💤 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 designed to assist with information, analysis, and creative tasks. My mission is to provide clear, accurate, and helpful responses to your questions or requests, ensuring that the information I share is accessible, understandable, and useful for a wide audience.

How can I assist you further?

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. L6N8738+1💤	0.94	“ ⏎⏎”“⏎ ⏎”“⏎”
2. L6N5065-1💤	0.93	“⏎”“ ‘”“⏎ ⏎”
3. L6N308+1💤	0.93	“⏎”“ ⏎”“ ⏎”
4. L3N8528+1🕒	0.92	“ ⏎”“⏎”“ ⏎⏎”
5. L8N5633-1💤	0.92	“⏎”“ ⏎”“ ⏎”
6. L7N2808+1💤	0.92	“ ⏎”“ ⏎⏎”“ _____”
7. L6N3877+1💤	0.92	“ ⏎”“⏎”“ ——”
8. L3N9174+1🕒	0.92	“ ⏎”“ ⏎⏎”“<\|im_end\|>”
9. L5N4274-1💤	0.92	“ ⏎”“ --”“⏎”
10. L6N7078-1💤	0.91	“ ⏎”“⏎”“ —”

Shadow specimen, apart from the ten: L6N5657+1🕒, -0.08.

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 5657, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.62, top-1 agreement 0.69) 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
L6N5657+1🕒 shadow specimen t0-v0.1	2.012	0.45	2.351	1.84	“ feedback”“ Feedback”“feedback”“-feedback”“Feedback”“反馈”“ control”“ system”
L6N5657-1 t0-v0.1	0.615	0.69	0.725	1.36	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.