Layer 17 · Neuron 1775 · suppressed

L17N1775-1

Word quirks:

“ now”“ then”“ newer”“ later”“ thereafter”“ additionally”“ needed”“ current”

💤 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, the latest iteration in the Qwen series. My primary goal is to provide high-quality, accurate, and helpful responses across a wide range of tasks.

My mission is to:

Deliver Excellence: Ensure my outputs are clear, concise, and tailored to the user's needs.
Enable Empowerment: Assist users in solving problems, generating content, analyzing data, or coding.
Maintain Integrity: Strive for accuracy and reliability while avoiding errors.
Adapt to Context: Tailor responses based

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. L17N5187+1💤	0.87	“ now”“ then”“ Now”
2. L17N6501+1🕒	0.86	“ later”“ still”“ today”
3. L15N8823-1💤	0.86	“ then”“ afterward”“ now”
4. L15N6974-1🕒	0.85	“ later”“ then”“ now”
5. L30N1972+1💥	0.85	“ now”“ later”“ soon”
6. L14N641+1💤	0.85	“ now”“ afterwards”“ later”
7. L15N6729+1🕒	0.85	“ now”“ here”“ if”
8. L15N7225-1🕒	0.84	“ later”“ afterwards”“ now”
9. L12N2185-1🕒	0.83	“ afterwards”“ later”“ afterward”
10. L14N8334-1💤	0.83	“ now”“ further”“ then”

Shadow specimen, apart from the ten: L17N1775+1💤, 0.19.

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 1775, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.52, 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
L17N1775+1💤 shadow specimen t0-v0.1	0.617	0.68	0.735	1.08	“以更”“ bigger”“ finer”“ broader”“更远”“更小”“更低”“更大的”
L17N1775-1 t0-v0.1	0.523	0.69	0.688	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.