Layer 12 · Neuron 7756 · suppressed

L12N7756-1

Word quirks:

“⏎”“ typically”“<|im_end|>”“ individual”“ often”“ individually”“ particular”“ within”

💤 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-scale language model developed by Alibaba Cloud. My mission is to provide high-quality, accurate, and diverse information while adhering to ethical standards. I aim to assist users in understanding complex topics, from science and technology to culture and history. In essence, my goal is to foster a deeper appreciation for the world's rich diversity of knowledge, promoting a more inclusive and meaningful dialogue between humans and machines.

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. L13N9051-1🕒	0.81	“ individual”“ individually”“ personally”
2. L11N7128-1🕒	0.80	“ usually”“ often”“ typically”
3. L9N2600+1💤	0.79	“ \"”“ specially”“ personally”
4. L12N5142-1🕒	0.79	“ sometimes”“ individually”“ specifically”
5. L12N3765+1💤	0.78	“ individual”“ individually”“ specific”
6. L8N8586+1💤	0.77	“ specific”“ generally”“ usually”
7. L13N8196+1🕒	0.76	“ individually”“ individual”“ personally”
8. L10N6444-1🕒	0.75	“ typically”“ individual”“ individually”
9. L13N9009+1🕒	0.75	“ new”“ often”“ sometimes”
10. L11N3647+1🕒	0.75	“ info”“ each”“ individual”

Shadow specimen, apart from the ten: L12N7756+1🕒, 0.28.

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 12, neuron 7756, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.79, top-1 agreement 0.67) 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
L12N7756+1🕒 shadow specimen t0-v0.1	0.826	0.62	1.019	1.28	“ your”“ you”“ my”“ I”“ Your”“ similar”“ seems”“ doesn”
L12N7756-1 t0-v0.1	0.790	0.67	0.979	1.26	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.