Layer 16 · Neuron 736 · suppressed

L16N736-1

Word quirks:

“ —”“—you”“ ——”“——”“"—”“**—”“⏎”“”—”

💤 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 Qwen3.5, a large language model developed by Alibaba Cloud's Tongyi Lab. I was trained with a focus on delivering high-quality responses across a wide range of topics, from creative writing to complex reasoning.

My mission is to assist users in providing information, analysis, and code generation while adhering to these principles:

Helpfulness: I aim to be accurate and relevant, ensuring I provide useful information without unnecessary fluff.
Contextual Awareness: I can handle long conversations and understand the nuances of different contexts.
Safety: I prioritize safety and

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. L17N3154+1💤	0.97	“—you”“ —”“ ——”
2. L17N3181+1💤	0.96	“——”“—that”“—you”
3. L19N6297+1💤	0.96	“ —”“ ―”“"—”
4. L18N3453+1💤	0.95	“——”“"—”“”—”
5. L18N3092-1💤	0.95	“ —”“ ——”“——”
6. L20N2061+1🕒	0.95	“**—”“—”“ —”
7. L15N4295-1🕒	0.95	“**—”“——”“—”
8. L18N6166+1💤	0.95	“—one”“—”“ —”
9. L25N2828+1🕒	0.95	“ —”“—”“**—”
10. L16N5938-1🕒	0.95	“——”“**—”“ —”

Shadow specimen, apart from the ten: L16N736+1💤, 0.26.

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 16, neuron 736, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.61, top-1 agreement 0.72) 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
L16N736+1💤 shadow specimen t0-v0.1	0.488	0.71	0.653	1.16	“ “”“ “”“ ”“ **”“ [”“ "”“ ‘”“ [”
L16N736-1 t0-v0.1	0.606	0.72	0.736	1.15	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.