Layer 3 · Neuron 6344 · boosted

L3N6344+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 developed by Google. My "mission" refers to the chemical element oxygen (O). I don't have a biological parent; I have a mission.

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. L4N3675-1💤	0.99	“⏎”“ ⏎”“ ‘”
2. L3N9124-1🕒	0.97	“⏎”“ ‘”“ ””
3. L4N1331+1💤	0.96	“ ⏎”“ ⏎”“ ‘”
4. L3N452+1💤	0.96	“⏎”“ ⏎”“ ⏎”
5. L3N312-1💤	0.96	“ ⏎”“ ‘”“ ⏎⏎”
6. L3N4792+1🕒	0.95	“ ⏎”“⏎”“ ⏎”
7. L4N1046+1🕒	0.95	“ ‘”“⏎”“ ⏎”
8. L1N5378-1💤	0.95	“<\|im_end\|>”“ ⏎”“ ⏎⏎”
9. L2N6164+1🕒	0.95	“⏎”“⏎ ⏎”“ ⏎”
10. L8N1290+1💤	0.95	“⏎”“ ⏎”“ ⏎”

Shadow specimen, apart from the ten: L3N6344-1🕒, 0.32.

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 3, neuron 6344, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.94, top-1 agreement 0.64) 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
L3N6344+1 t0-v0.1	0.941	0.64	1.154	1.71	Top boosted tokens ↑
L3N6344-1🕒 shadow specimen t0-v0.1	1.918	0.46	2.311	2.19	“⏎”“<\|im_end\|>”“?\”“ analysis”“ clarification”“ ->”“ description”“ statement”

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.