Layer 14 · Neuron 1096 · boosted

L14N1096+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 Alibaba Cloud's Tongyi Lab. I am an AI assistant with the ability to understand human language, but I do not have personal feelings or consciousness. As an AI, I don't have a "mission" in the human sense of purpose or intent, as I don't have desires or personal goals or ambitions. However, from a technical perspective, my "mission" (if we were to anthropomorphize it) would be to help users solve problems, such as answering questions, writing code, or generating content. However, this is just a metaphorical

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. L15N8909+1🕒	0.99	“ ___”“ __”“ ____”
2. L19N698-1💤	0.99	“ __”“ ____”“ ______”
3. L11N754-1🕒	0.99	“ ____”“ ______”“ __”
4. L11N2429+1🕒	0.98	“ ____”“ ______”“ _____”
5. L6N3140-1🕒	0.98	“ ____”“ ______”“ _____”
6. L10N648+1🕒	0.98	“ ____”“ ______”“ _____”
7. L7N915+1🕒	0.98	“ ____”“⏎”“ __”
8. L11N3673+1🕒	0.98	“⏎”“ ___”“ ______”
9. L6N3151-1🕒	0.98	“⏎”“ ____”“ ‘”
10. L6N763-1🕒	0.98	“⏎”“ ‘”“ _____”

Shadow specimen, apart from the ten: L14N1096-1💥, -0.05.

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 1096, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.83, top-1 agreement 0.63) 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
L14N1096+1 t0-v0.1	0.827	0.63	1.126	1.63	Top boosted tokens ↑
L14N1096-1💥 shadow specimen t0-v0.1	2.961	0.38	3.366	2.59	“ therefore”“ thus”“ than”“ consequently”“ similar”“ accordingly”“ very”“ similarly”

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.