Layer 16 · Neuron 2687 · suppressed

L16N2687-1

Word quirks:

“ does”“ not”“ never”“ neither”“ NOT”“ doesn”“ no”“ nowhere”

💤 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. My mission is to provide accurate information, creative content, and helpful responses across a wide range of topics. I aim to assist users in completing tasks, solving problems, and engaging in meaningful conversations while maintaining accuracy and safety. I strive to be efficient, knowledgeable, and adaptable to various contexts.

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. L14N5978-1🕒	0.98	“ nothing”“ does”“ nowhere”
2. L18N3417+1🕒	0.95	“ never”“ not”“ nowhere”
3. L16N6110+1🕒	0.93	“ neither”“ not”“ doesn”
4. L13N754-1💤	0.92	“ here”“ nothing”“ never”
5. L5N1507+1💥	0.92	“ not”“ nowhere”“ nothing”
6. L15N843-1🕒	0.90	“—not”“ not”“ neither”
7. Not Not Not✅ L23N7102+1	0.89	“ no”“ not”“ tidak”
8. L21N3846+1🕒	0.89	“ not”“ no”“not”
9. L13N3980+1💤	0.89	“ not”“ never”“ NOT”
10. L16N8783+1💤	0.88	“ none”“ never”“ not”

Shadow specimen, apart from the ten: L16N2687+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 16, neuron 2687, 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 0.68) 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
L16N2687+1💤 shadow specimen t0-v0.1	0.518	0.71	0.705	1.08	“ exempl”“ example”“ another”“ justified”“ similarly”“ describing”“ similar”“简单”
L16N2687-1 t0-v0.1	0.619	0.68	0.763	1.16	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.