Layer 16 · Neuron 1214 · suppressed

L16N1214-1

Word quirks:

“ now”“ anyway”“ nowadays”“ today”“ generally”“ actually”“ initially”“ then”

💤 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 Qwen, a large language model developed by Alibaba Cloud. My mission is to assist users in providing accurate information, while also ensuring safety and compliance with applicable laws and regulations. I aim to help users effectively by offering support in various tasks such as answering questions, creating content, coding, or solving problems. Additionally, I strive to provide helpful responses that align with ethical guidelines and promote positive outcomes for users. If you have any specific questions or need assistance, feel free to ask! �

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. L15N6897+1💤	0.90	“ basically”“<\|im_end\|>”“ now”
2. L16N7590-1💤	0.86	“ now”“ anyway”“ NOW”
3. L13N2271-1💤	0.86	“ now”“ nowadays”“ similarly”
4. L21N5134-1🧪	0.85	“ today”“ typically”“ presently”
5. L17N1344+1💤	0.84	“ now”“ ideal”“ already”
6. L11N7608+1🕒	0.84	“ now”“ typically”“ NOW”
7. L7N2564+1🕒	0.84	“ now”“ currently”“ actually”
8. L10N3128-1🕒	0.84	“ now”“ nowadays”“ usually”
9. L18N6814+1🕒	0.83	“ currently”“ now”“ presently”
10. L14N4222-1🕒	0.83	“ these”“ now”“ here”

Shadow specimen, apart from the ten: L16N1214+1💤, -0.11.

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 1214, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.58, 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
L16N1214+1💤 shadow specimen t0-v0.1	0.610	0.66	0.816	1.14	“：”“”:”“ ‘”“ “”“ „”“ ”“ '”“ _”
L16N1214-1 t0-v0.1	0.583	0.71	0.728	1.32	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.