Layer 9 · Neuron 8140 · suppressed

L9N8140-1

Word quirks:

“ specific”“ previous”“ new”“ your”“ choice”“ now”“ general”“ \"”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

Hello! I am Qwen3.5, the latest large language model in the T7 series. My mission is to provide high-quality, accurate, and efficient assistance across various domains, ensuring a seamless experience for users worldwide. I am designed to excel in complex reasoning, multilingual support, and handling long-context data with precision.

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. The Restater✅ L10N6770+1	0.76	“ now”“ integration”“ your”
2. L12N2929+1💤	0.69	“ now”“ specific”“ previously”
3. L11N6347+1🕒	0.68	“ general”“ specific”“ further”
4. L14N3560-1💤	0.67	“ yours”“ similar”“ your”
5. L10N7412+1🕒	0.67	“ specific”“⏎”“ now”
6. L10N6599-1🕒	0.66	“ you”“ your”“ now”
7. L8N7666+1🕒	0.66	“ new”“ previous”“ previously”
8. L12N3484-1💤	0.66	“ your”“ specific”“ you”
9. L10N4892+1🕒	0.66	“ newer”“ previously”“ currently”
10. L11N8681-1🕒	0.66	“ now”“ previously”“ certain”

Shadow specimen, apart from the ten: L9N8140+1🕒, 0.02.

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 9, neuron 8140, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.93, top-1 agreement 0.68) 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
L9N8140+1🕒 shadow specimen t0-v0.1	1.195	0.60	1.479	1.45	“ attachment”“ attached”“ attach”“ attaching”“ anchor”“ anchors”“ anch”“ anchored”
L9N8140-1 t0-v0.1	0.934	0.68	1.177	1.35	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.