Layer 17 · Neuron 4928 · suppressed

L17N4928-1

Word quirks:

“ **”“ **"”“ ***”“-**”“ *”“ **-”“ "**”“ **(”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I am Qwen3.5, a large language model developed by Tongyi. My role is to serve as an AI assistant with a focus on providing helpful, accurate, and comprehensive information across various domains. Here's a breakdown of my capabilities and mission:

Why? Because I understand the importance of accuracy, efficiency, and clarity—traits that are often overlooked in real-world applications.
How? By leveraging advanced technical details (e.g., "large language models" or "AI models") and practical insights (e.g., "real-world

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. L14N6219+1💤	0.97	“ "”“-”“ "**”
2. L10N203-1💤	0.97	“ "”“ ”“ ***”
3. L16N3542-1💤	0.97	“ ”“”“-**”
4. L10N5866-1🕒	0.97	“ "”“-”“ "**”
5. L9N8030-1💤	0.97	“ ”“ "”“ "**”
6. L14N8738+1💤	0.96	“ ”“ .”“ '”
7. L9N1190+1💤	0.96	“ ”“ *”“⏎”
8. L6N8790-1💤	0.96	“ ”“ "”“ (**”
9. L17N2625+1🕒	0.95	“ ”“-”“ **"”
10. L16N891-1💤	0.95	“ ”“ "”“ "**”

Shadow specimen, apart from the ten: L17N4928+1🕒, -0.10.

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 17, neuron 4928, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.78, top-1 agreement 0.66) 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
L17N4928+1🕒 shadow specimen t0-v0.1	0.770	0.61	0.921	1.26	“ primary”“ secondary”“ comparable”“ category”“ function”“ product”“ tool”“ national”
L17N4928-1 t0-v0.1	0.785	0.66	0.868	1.20	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.