Layer 16 · Neuron 5747 · suppressed

L16N5747-1

Word quirks:

“ actually”“ isn”“ wasn”“ indeed”“ shouldn”“ seems”“ really”“ aren”

💤 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 Tongyi Lab. My identity is rooted in the fact that I am an AI assistant designed to be helpful, harmless, and honest—principles that guide my interactions.

What is my mission?
To empower users with reliable, accurate, and context-aware assistance. Whether you need help solving problems, learning new things, or creating content, I aim to provide value through:

Comprehensive capabilities (text generation, coding, analysis)
Real-world application (multilingual support, task execution)

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. L12N3605-1💤	0.93	“ doesn”“ actually”“ isn”
2. L12N901+1🕒	0.90	“ indeed”“ isn”“ seems”
3. L12N1872-1🕒	0.90	“ doesn”“ isn”“ aren”
4. L13N2645+1🕒	0.90	“ doesn”“ isn”“ actually”
5. L11N7890-1🕒	0.90	“ supposedly”“ already”“ actually”
6. L11N3080-1🕒	0.89	“ doesn”“ isn”“ basically”
7. L16N6500+1🕒	0.89	“ actually”“ isn”“ aren”
8. L15N5634+1🕒	0.89	“ isn”“ doesn”“ aren”
9. L12N4645-1💤	0.89	“ doesn”“ isn”“ but”
10. L14N7186-1🕒	0.89	“ also”“ isn”“ doesn”

Shadow specimen, apart from the ten: L16N5747+1🕒, 0.05.

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 5747, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.57, top-1 agreement 0.69) 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
L16N5747+1🕒 shadow specimen t0-v0.1	0.653	0.68	0.859	1.25	“ called”“ if”“ name”“称为”“ mainly”“ again”“ Called”“ what”
L16N5747-1 t0-v0.1	0.572	0.69	0.705	1.31	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.