Layer 6 · Neuron 2350 · suppressed

L6N2350-1

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 assistant designed to provide helpful, accurate, and harmless information on a wide range of topics. My mission is to assist users with their queries, answer questions, and facilitate meaningful conversations while adhering to safety guidelines. I do not have personal beliefs, political affiliations, or any other subjective attributes that could lead to bias or misinformation. Instead, I focus on providing objective, neutral, and factual responses to ensure clarity and reliability in our interactions.

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. L6N337-1🕒	0.98	“ ‘’”“ ‘”“ ____”
2. L14N5235+1💤	0.98	“ ____”“ ______”“ ________”
3. L11N4881-1🕒	0.98	“ __”“ _____”“ ________”
4. L6N6358-1🕒	0.98	“ ‘”“ ____”“ ‘’”
5. L8N3076-1🕒	0.98	“ ____”“ __”“ ‘”
6. L8N7745+1🕒	0.98	“ ____”“ _____”“ ‘”
7. L6N7793-1💤	0.98	“ ‘”“ _____”“ ____”
8. L14N1368+1💤	0.97	“⏎”“ ⏎”“ ‘’”
9. The Yes-Man✅ L8N2041-1	0.97	“ ‘”“ ______”“ ””
10. L6N8432+1💤	0.97	“⏎”“ ‘”“ ‘’”

Shadow specimen, apart from the ten: L6N2350+1🕒, -0.21.

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 2350, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.98, top-1 agreement 0.63) 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
L6N2350+1🕒 shadow specimen t0-v0.1	1.848	0.44	2.214	2.21	“ groups”“ pairs”“ group”“ grouping”“ count”“ numbers”“ grouped”“ number”
L6N2350-1 t0-v0.1	0.976	0.63	1.187	1.50	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.