Layer 17 · Neuron 4718 · suppressed

L17N4718-1

Word quirks:

“ ‘”“‘”“’d”“ ’”“’ll”“ “”“’s”“ “[”

💤 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 Qwen3.1, a large language model developed by Tong Liao, part of the Alibaba group. My mission is to provide accurate, helpful, and ethical AI assistance across a wide range of topics and contexts. I aim to enhance your capabilities as an AI assistant by integrating advanced features like long-context understanding, multilingual support, and specialized knowledge in various domains. 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. L18N4608+1💤	0.98	“ “”“ ‘”“’ll”
2. L16N1119+1💤	0.97	“ ‘”“ “[”“’d”
3. L18N3551+1💤	0.96	“ ‘”“’d”“ “”
4. L18N5164+1🕒	0.95	“ “”“ ‘”“ “[”
5. L6N74-1🕒	0.95	“ ‘”“’d”“’s”
6. L18N2917-1💤	0.95	“ ‘”“ “”“’s”
7. L18N8023+1💤	0.95	“ ‘”“ “”“‘”
8. L18N2230-1💤	0.95	“ ‘”“ “[”“‘”
9. L14N5866-1💤	0.95	“ ‘”“ “”“‘”
10. L16N889-1💤	0.95	“ ‘”“ **‘”“’ll”

Shadow specimen, apart from the ten: L17N4718+1💤, 0.01.

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 4718, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.44, top-1 agreement 0.76) 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
L17N4718+1💤 shadow specimen t0-v0.1	0.500	0.74	0.616	1.17	“ usually”“ additionally”“往往”“ often”“ typically”“通常”“ ”“：*”
L17N4718-1 t0-v0.1	0.439	0.76	0.567	1.25	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.