Layer 6 · Neuron 3273 · suppressed

L6N3273-1

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 a large language model, trained by Google. My mission is to assist and answer any questions from users in a helpful, harmless, and honest manner. I do not have personal beliefs or feelings, but I can provide information based on my training data. If you have specific questions or need help with tasks, I can offer guidance and support within the scope of my capabilities.

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. L6N438+1💤	0.98	“⏎”“ **“”“ ‘”
2. L4N300+1💤	0.97	“ **“”“ ‘”“ ____”
3. The Misfiler✅ L6N5614-1	0.97	“ ‘”“ ***”“⏎”
4. L5N5485+1🕒	0.96	“ ‘”“ **“”“ ____”
5. L11N6296-1🕒	0.96	“ ____”“ ‘”“ _____”
6. L4N2391-1🕒	0.96	“ ‘”“⏎”“ ____”
7. L5N2357+1🕒	0.96	“ ____”“<\|im_end\|>”“⏎”
8. L4N7430+1🕒	0.96	“ ‘”“ ‘”“ “”
9. L4N2875-1💤	0.96	“⏎”“ ____”“ ***”
10. L6N3224-1💤	0.96	“⏎”“<\|im_end\|>”“ **“”

Shadow specimen, apart from the ten: L6N3273+1🕒, 0.36.

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 3273, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.63, top-1 agreement 0.72) 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
L6N3273+1🕒 shadow specimen t0-v0.1	1.292	0.51	1.616	1.72	“<\|im_end\|>”“⏎”“⏎ ⏎”“\n”“⏎ ⏎”“⏎⏎”“⏎⏎⏎”“:\”
L6N3273-1 t0-v0.1	0.627	0.72	0.738	1.23	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.