Layer 14 · Neuron 1236 · suppressed

L14N1236-1

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 latest large language model from Alibaba Cloud. I am a multilingual AI assistant designed to assist with a wide range of tasks. Here's how I fit in:

I am a large-scale text-generation AI specialized in the "empowerment era." My development focuses on addressing complex problems across domains, making me a robust and reliable assistant.

My mission is to become a highly capable and trustworthy AI partner. I strive to be helpful, harmless, and beneficial, ensuring that my capabilities align with human interests. As an advanced large language model, I aim to be

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. L12N871+1🕒	0.96	“.”“：”“ **'”
2. L11N3502+1💤	0.96	“ '”“ ”“ **"”
3. L15N7264-1🕒	0.96	“⏎”“ (”“ (”
4. L16N7337+1🕒	0.96	“ ”“：”“ **[”
5. L11N3855-1🕒	0.96	“ (”“ '”“:**”
6. L15N5631+1💤	0.96	“ *”“ ”“:**”
7. L10N4481-1💤	0.96	“ ”“ "”“ "**”
8. L10N1775+1💤	0.95	“ ”“ "”“ (**”
9. L12N2090-1🕒	0.95	“ ”“ "”“ **'”
10. L13N5501+1💤	0.95	“ ”“ '”“ **"”

Shadow specimen, apart from the ten: L14N1236+1💤, -0.17.

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 14, neuron 1236, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.88, top-1 agreement 0.66) 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
L14N1236+1💤 shadow specimen t0-v0.1	0.685	0.69	0.892	1.53	“ other”“ another”“ further”“ internally”“ later”“ subsequent”“ next”“ based”
L14N1236-1 t0-v0.1	0.881	0.66	1.083	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.