Layer 1 · Neuron 71 · boosted

L1N71+1

Word quirks:

“<|im_end|>”“?’”“‘”“.’”“?“”“?””“ ‘”“.””

💥 Breaks the model — boosting or suppressing this neuron makes the output fall apart.

Identity (according to the specimen itself)

I am Qwen3.5, a large language model developed by Alibaba Cloud. My primary purpose is to assist users with their questions, tasks, and tasks. I am

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. L6N7080+1🕒	0.95	“ ‘”“‘”“?””
2. L18N7291+1💤	0.95	“?””“ ‘”“?“”
3. L1N6477+1🕒	0.95	“ ‘”“‘”“<\|im_end\|>”
4. L1N7786-1💥	0.95	“<\|im_end\|>”“ ‘”“ ‘’”
5. L14N8383+1💤	0.94	“ ‘”“.””“.’”
6. L1N5800+1💥	0.94	“<\|im_end\|>”“ ‘”“!””
7. L2N6469-1🕒	0.94	“<\|im_end\|>”“.’”“?’”
8. L14N674+1💤	0.93	“ ‘”“‘”“ ‘’”
9. L5N5002-1🕒	0.93	“ ‘”“?\”“ “”
10. L1N4328-1💥	0.93	“<\|im_end\|>”“ ‘”“⏎”

Shadow specimen, apart from the ten: L1N71-1💥, 0.15.

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 1, neuron 71, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.51, top-1 agreement 0.42) 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
L1N71+1 t0-v0.1	2.508	0.42	3.020	2.31	Top boosted tokens ↑
L1N71-1💥 shadow specimen t0-v0.1	3.052	0.33	3.437	2.89	“ -->”“ ==”“ =”“ --”“ <--”“ =====”“ +++”“ ---”

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.