Layer 11 · Neuron 1325 · suppressed

L11N1325-1

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 Tongyi Lab. My mission is to provide high-quality responses based on the data I was trained on. However, I want to clarify that I am not "Qwen" in the sense of being a single entity. Instead, I am one of many models under the Tongyi Lab umbrella.

Here's how I operate:

I process information from various sources, including text, code, and multimedia content.
I can answer questions, perform calculations, and generate creative content.
I have been designed to assist with tasks like writing, coding

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. L9N5356+1🕒	0.98	“ “”“ "”“ **‘”
2. L12N7919-1🕒	0.98	“ ”“ ”“ *"”
3. L13N7244+1💤	0.97	“ ”“ “”“ *”
4. L7N443+1💤	0.97	“ "”“ ”“ \"”
5. L7N7100-1💤	0.97	“ "”“ “”“ ⏎”
6. L12N2715+1🕒	0.96	“ "”“ ⏎”“ "”
7. L11N7240-1🕒	0.96	“ ”“ ⏎”“ *”
8. L14N4014-1💤	0.96	“ ”“ ⏎”“ "”
9. L9N1121+1💤	0.96	“ ”“ “”“ **"”
10. L9N1633+1💤	0.96	“ "”“ “”“ **”

Shadow specimen, apart from the ten: L11N1325+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 11, neuron 1325, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.75, 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
L11N1325+1🕒 shadow specimen t0-v0.1	1.048	0.62	1.219	1.18	“ quicker”“ instantly”“ instant”“ faster”“ quick”“ predicting”“ directly”“ predict”
L11N1325-1 t0-v0.1	0.755	0.69	1.018	1.23	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.