Layer 6 · Neuron 7133 · boosted

L6N7133+1

Word quirks:

“ "**”“ **"”“ **“”“ \"”“ usually”“ **'”“ description”“ **‘”

💤 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 large language model developed by Alibaba Cloud. I am designed to be highly capable and versatile, with significant improvements over my predecessor, Qwen. My capabilities include:

Advanced Text Generation: I can generate complex text with greater fluency, making me exceptionally adept at handling intricate tasks and creative writing.
Enhanced Reasoning: I possess superior reasoning abilities, allowing me to solve complex problems and make nuanced decisions more effectively than before.
Innovative Planning: I excel in planning and executing multi-step strategies, enabling me to tackle sophisticated challenges with precision and

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. L6N8346+1💤	0.95	“ "”“ “”“ **«”
2. L9N3331-1💤	0.94	“ \"”“ '”“ “”
3. L6N6382-1💤	0.94	“ "”“ “”“ **'”
4. L6N5839-1💤	0.94	“ "”“ “”“ specific”
5. L15N2501-1💤	0.93	“ “”“ "”“ **'”
6. L6N8663+1💤	0.93	“ ‘”“ '”“ ‘”
7. L6N5548-1🕒	0.93	“ "”“ “”“ **'”
8. L7N3156+1💤	0.93	“ **"”“ '”“ "”
9. L15N5140-1💤	0.93	“ '”“ "”“ "**”
10. L7N7233+1🕒	0.93	“ "”“ “”“ "**”

Shadow specimen, apart from the ten: L6N7133-1🕒, -0.13.

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 6, neuron 7133, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.68, 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
L6N7133+1 t0-v0.1	0.680	0.68	0.850	1.34	Top boosted tokens ↑
L6N7133-1🕒 shadow specimen t0-v0.1	1.782	0.48	2.101	2.02	“ satisfaction”“ satisfactory”“ satisfied”“ Satisfaction”“ overall”“<\|im_end\|>”“ happiness”“ happy”

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.