Layer 11 · Neuron 652 · boosted

L11N652+1

Word quirks:

“:\”“.\"”“ ⏎⏎”“:\"”“.\”“ ‘”“:'”“.””

💤 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, a large language model developed by Alibaba Cloud. My mission is to provide high-quality, accurate, and safe responses that meet the diverse needs of users across various industries. I strive to offer precise and relevant information while ensuring safety and reliability.

To achieve this, I have been specifically designed with advanced capabilities in areas such as deep reasoning, visual analysis, and code generation. By integrating these features, I can effectively handle complex tasks and provide valuable insights for users.

Here are some key features that enable me to deliver high-quality results:

Advanced Language Understanding: I can accurately interpret nuanced instructions

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. L5N1331+1🕒	0.95	“.\"”“?\”“.\”
2. L3N6906-1🕒	0.95	“:\”“.\”“ ‘”
3. L3N6404-1🕒	0.94	“⏎”“."”“:"”
4. L5N4844+1🕒	0.94	“?\”“⏎”“:\”
5. L5N537-1🕒	0.93	“.\"”“ -”“:\”
6. L5N3888-1💤	0.93	“ \"”“ ‘”“⏎”
7. L4N6187+1🕒	0.93	“:\”“ \"”“?\”
8. L6N3424+1💤	0.93	“ \"”“ '”“.\"”
9. L13N574-1🕒	0.93	“.\"”“:\”“.\”
10. L4N1482+1🕒	0.93	“?\”“ ‘”“.\"”

Shadow specimen, apart from the ten: L11N652-1🕒, 0.20.

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 11, neuron 652, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.78, top-1 agreement 0.64) 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
L11N652+1 t0-v0.1	0.780	0.64	0.922	1.26	Top boosted tokens ↑
L11N652-1🕒 shadow specimen t0-v0.1	0.910	0.66	1.163	1.35	“ description”“ "”“ "”“ describing”“ **”“ defining”“ explanation”“ explaining”

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.