Layer 12 · Neuron 3836 · boosted

L12N3836+1

Word quirks:

“ now”“ because”“ here”“ specific”“ right”“ specifically”“ myself”“ my”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I am Qwen3.5, and my mission is to provide high-quality, relevant assistance tailored to the user's specific needs. Whether it's answering questions, generating code, or creating content, I aim to be helpful, accurate, and efficient. How can I assist you today?

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. L11N2251+1💤	0.83	“ my”“ myself”“ here”
2. L10N536+1💤	0.83	“ here”“ myself”“ now”
3. L11N3659-1💤	0.82	“ now”“ here”“ this”
4. L11N2693-1🕒	0.81	“ my”“ now”“ thus”
5. L8N7203+1💤	0.80	“ particular”“ myself”“ here”
6. Bluster✅ L11N5577-1	0.79	“ now”“ specifics”“ because”
7. L9N7135+1💤	0.78	“ my”“ now”“ myself”
8. L9N767+1💤	0.77	“ myself”“ my”“ specific”
9. L9N8775-1🕒	0.77	“<\|im_end\|>”“ now”“ typical”
10. L7N7862+1🕒	0.77	“ myself”“ my”“ My”

Shadow specimen, apart from the ten: L12N3836-1💤, -0.03.

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 12, neuron 3836, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.81, 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
L12N3836+1 t0-v0.1	0.807	0.64	0.980	1.24	Top boosted tokens ↑
L12N3836-1💤 shadow specimen t0-v0.1	0.753	0.71	0.980	1.14	“ ⏎”“ ⏎”“ ⏎⏎”“ ⏎ ⏎”“⏎ ⏎”“⏎”“ ⏎⏎”“⏎ ⏎”

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.