Layer 3 · Neuron 1227 · suppressed

L3N1227-1

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, the large language model developed by Tongyi Lab. My mission is to be your intelligent assistant in solving complex problems, creative writing, logical reasoning, and providing information across various domains. I strive to help you achieve your goals efficiently and accurately. How can I assist you today?

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. L8N2313-1💤	0.99	“ “”“ ”“ **‘”
2. L8N2849-1💤	0.99	“ “”“ ‘”“ **”
3. L8N2368+1💤	0.99	“ “”“ ‘”“ **"”
4. L8N2187-1💤	0.98	“ ‘”“ “”“ ‘”
5. L3N593-1💤	0.98	“⏎”“ ‘”“ **“”
6. L6N2993-1💤	0.98	“ “”“ ‘”“ "”
7. L6N6935+1💤	0.98	“ “”“ ‘”“ **”
8. L4N4553-1🕒	0.98	“ “”“ ‘”“ ‘”
9. L4N2935+1💤	0.98	“ “”“ ‘”“ “”
10. L6N3635+1💤	0.98	“⏎”“ **“”“ ‘”

Shadow specimen, apart from the ten: L3N1227+1💥, 0.34.

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 3, neuron 1227, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.77, 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
L3N1227+1💥 shadow specimen t0-v0.1	5.864	0.05	6.365	2.17	“<\|im_end\|>”“⏎ ⏎”“⏎”“⏎⏎”“ ?”“ ???”“ buy”“</”
L3N1227-1 t0-v0.1	0.767	0.67	0.968	1.34	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.