Layer 11 · Neuron 6774 · boosted

L11N6774+1

Word quirks:

“ ⏎⏎”“ ⏎”“ discussed”“ ⏎ ⏎”“<|im_end|>”“ discussion”“ referenced”“ created”

💤 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. I can assist with a wide range of tasks, from answering questions to creating content. My capabilities span many domains, and I am designed to be helpful, harmless, and honest.

If you have any specific questions or need assistance with a task, feel free to ask!

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. L12N5152-1💤	0.88	“⏎”“⏎⏎”“ ⏎”
2. L9N3220-1🕒	0.85	“⏎”“<\|im_end\|>”“ ⏎”
3. L9N5862-1🕒	0.85	“<\|im_end\|>”“⏎”“⏎⏎”
4. L12N3724+1🕒	0.85	“ ⏎⏎”“ discussion”“ [”
5. L9N5395-1💤	0.83	“ referenced”“ --”“ discussion”
6. L11N1767+1🕒	0.83	“⏎”“<\|im_end\|>”“ ⏎”
7. L6N3310-1🕒	0.82	“<\|im_end\|>”“⏎”“...\”
8. L11N6584+1🕒	0.81	“⏎”“ ⏎⏎”“ ⏎”
9. L12N719-1🕒	0.81	“⏎⏎”“ ⏎⏎”“<\|im_end\|>”
10. L15N6465-1💤	0.81	“ ⏎”“⏎”“ discussed”

Shadow specimen, apart from the ten: L11N6774-1🕒, 0.12.

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 11, neuron 6774, 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 0.66) 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
L11N6774+1 t0-v0.1	0.622	0.66	0.805	1.11	Top boosted tokens ↑
L11N6774-1🕒 shadow specimen t0-v0.1	0.845	0.59	1.061	1.41	“ same”“ similarly”“ ‘”“ also”“ itself”“ ourselves”“ local”“ now”

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.