Layer 13 · Neuron 1298 · boosted

L13N1298+1

Word quirks:

“ now”“<|im_end|>”“ you”“ maybe”“?...”“...*”“ here”“ Now”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

Answered — readability check pending

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. L6N8041-1🕒	0.80	“ now”“<\|im_end\|>”“...””
2. L13N8578+1🕒	0.77	“ now”“ here”“...**”
3. L13N6734+1💤	0.75	“ really”“ maybe”“ thinking”
4. L13N4049+1🕒	0.74	“ now”“?...”“...\”
5. L12N7356-1💤	0.73	“ here”“ you”“ --”
6. L14N7044+1🕒	0.73	“ now”“ maybe”“ here”
7. L14N8315+1🕒	0.71	“ now”“ NOW”“ may”
8. L14N6671-1💤	0.71	“ now”“ your”“ again”
9. L12N4548+1💤	0.71	“ now”“ indeed”“ here”
10. L11N1706-1🕒	0.71	“<\|im_end\|>”“ now”“ sometimes”

Shadow specimen, apart from the ten: L13N1298-1💤, 0.02.

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 13, neuron 1298, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L13N1298+1 t0-v0.1	1.323	0.51	1.621	2.11	Top boosted tokens ↑
L13N1298-1💤 shadow specimen t0-v0.1	0.700	0.68	0.896	1.15	“!"”“!”“!**”“!)”“"!”“ crafted”“ actually”“!")”

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.