Layer 7 · Neuron 8108 · boosted

L7N8108+1

Word quirks:

“⏎”“<|im_end|>”“ ‘”“⏎⏎⏎”“ description”“ --”“ reference”“.`”

💤 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. My mission is to provide intelligent, context-aware assistance for users across various domains—including text analysis, code generation, data visualization, and more—by leveraging my advanced capabilities in natural language understanding and reasoning. I aim to empower developers, researchers, and organizations to build better tools, systems, and applications that are more efficient, scalable, and user-friendly.

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. L4N8208-1🕒	0.87	“⏎”“ --”“ '”
2. L5N619+1💤	0.87	“⏎⏎”“⏎”“ '”
3. L3N3681-1🕒	0.87	“ `”“<\|im_end\|>”“⏎”
4. L5N4112-1🕒	0.87	“⏎”“⏎⏎⏎”“ ‘”
5. L5N4918-1🕒	0.86	“⏎”“ ‘”“?\”
6. L3N1304-1🕒	0.86	“ -”“ ‘”“ ⏎”
7. L3N6312+1🕒	0.86	“⏎”“<\|im_end\|>”“.”
8. L4N4686+1🕒	0.86	“⏎”“ ‘”“ '”
9. L4N710+1🕒	0.86	“⏎”“<\|im_end\|>”“ -”
10. L3N6705-1🕒	0.86	“⏎”“ ‘”“ '”

Shadow specimen, apart from the ten: L7N8108-1🕒, -0.09.

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 7, neuron 8108, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.57, top-1 agreement 0.70) 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
L7N8108+1 t0-v0.1	0.571	0.70	0.708	1.27	Top boosted tokens ↑
L7N8108-1🕒 shadow specimen t0-v0.1	2.035	0.47	2.409	1.93	“ circle”“ representation”“ circles”“ shape”“ circular”“ ellipse”“ circumference”“ representing”

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.