Layer 23 · Neuron 4388 · suppressed

L23N4388-1

Word quirks:

“ stable”“ Stable”“稳定”“-bre”“ stead”“稳定的”“-unit”“ unit”

💤 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 Q3, a large-scale advanced AI model developed by the StableE6 team. My primary mission is to provide users with high-quality, accurate, and helpful information across diverse domains such as science, technology, health, and daily life. I aim to support users in solving problems, enhancing understanding, and making informed decisions through clear, concise, and personalized interactions. Whether you need guidance on complex topics or simple tasks, I strive to be a reliable and engaging companion in your learning and problem-solving process. 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. L25N3324+1🕒	0.87	“ stable”“stable”“ Stable”
2. L25N5113-1🕒	0.87	“ stable”“ Stable”“稳定”
3. L31N7171-1💥	0.87	“稳定”“ stabil”“稳定的”
4. L21N6893-1🕒	0.87	“稳定”“ stable”“stable”
5. L24N7702+1🕒	0.87	“ stable”“ Stable”“稳定”
6. L29N3549-1🕒	0.86	“ stable”“stable”“ Stable”
7. L23N6107-1🕒	0.86	“ stable”“ Stable”“稳定的”
8. L24N1197-1💤	0.86	“ stable”“稳定”“稳定性”
9. L25N5812-1🕒	0.86	“稳定”“ Stabil”“ Stable”
10. L17N7530+1🕒	0.86	“ stable”“ stabilized”“稳固”

Shadow specimen, apart from the ten: L23N4388+1🕒, 0.17.

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 23, neuron 4388, 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 0.71) 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
L23N4388+1🕒 shadow specimen t0-v0.1	0.805	0.72	0.802	1.24	“红”“ asc”“уж”“ Red”“囊”“udem”“Fre”“ dt”
L23N4388-1 t0-v0.1	0.621	0.71	0.721	1.21	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.