Layer 9 · Neuron 3434 · suppressed

L9N3434-1

Word quirks:

“ gift”“ gifts”“ Gift”“礼物”“ Gifts”“gift”“Gift”“ nicely”

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

Identity (according to the specimen itself)

I'm not sure who you are asking about. Do you have a specific person in mind?

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. L31N8053-1💥	0.99	“ Gift”“ gift”“gift”
2. L6N8547-1🕒	0.99	“ gift”“ gifts”“ Gift”
3. L24N7383-1🕒	0.98	“ gifts”“ gift”“gift”
4. L5N7870+1💥	0.97	“ gift”“ gifts”“ Gift”
5. L2N4328+1💥	0.97	“<\|im_end\|>”“ gift”“ gifts”
6. L19N5656-1🕒	0.96	“ gift”“ gifts”“ Gift”
7. L26N1471-1🕒	0.96	“ gift”“ gifts”“Gift”
8. L25N3166+1🕒	0.95	“ gift”“ Gift”“Gift”
9. L22N8235+1🕒	0.92	“ gift”“ generosity”“Gift”
10. L24N7025+1🕒	0.92	“ gift”“ Gift”“ gifts”

Shadow specimen, apart from the ten: L9N3434+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 9, neuron 3434, 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
L9N3434+1💤 shadow specimen t0-v0.1	0.934	0.65	1.231	1.39	“ identification”“ **“”“ description”“ driver”“ statements”“ interaction”“ drivers”“ pilot”
L9N3434-1 t0-v0.1	1.436	0.53	1.737	1.76	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.