Layer 13 · Neuron 8147 · boosted

L13N8147+1

Word quirks:

“ ⏎”“ ⏎⏎”“ first”“ __”“ ________”“⏎”“ _____”“ now”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

Hello! I am Qwen3.5, a large-scale language model developed by Tongyi Lab. My mission is to provide high-quality assistance across diverse domains:

Comprehensive Knowledge: From basic facts to advanced research in fields like science, history, and technology.
Multilingual Support: Fluent communication in over 100 languages worldwide, including Chinese, English, and French.
Advanced Capabilities:
Deep Reasoning: Solving complex problems in mathematics, logic, and scientific analysis.
Multimodal Understanding: Processing and interpreting visual data (images,

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. L7N8650-1💤	0.94	“ ⏎”“ ⏎⏎”“⏎”
2. L10N4097+1🕒	0.90	“ ⏎”“⏎”“ start”
3. L8N1240-1💤	0.90	“ ⏎”“ ⏎⏎”“ ______”
4. L10N4915+1💤	0.90	“ ⏎”“ ⏎”“ ⏎⏎”
5. L13N7661+1💤	0.90	“⏎”“ actually”“ ⏎”
6. L8N2525-1💤	0.90	“⏎”“ ⏎”“ ____”
7. L6N2230+1💤	0.90	“⏎”“ _____”“ ⏎”
8. L7N3840-1🕒	0.90	“ ⏎”“⏎”“ ⏎”
9. L9N3844+1💤	0.90	“⏎”“ ⏎”“ ⏎”
10. L9N3681-1🕒	0.89	“ ⏎”“⏎”“ ⏎”

Shadow specimen, apart from the ten: L13N8147-1🕒, 0.13.

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 13, neuron 8147, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.76, top-1 agreement 0.64) 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
L13N8147+1 t0-v0.1	0.757	0.64	0.941	1.41	Top boosted tokens ↑
L13N8147-1🕒 shadow specimen t0-v0.1	1.048	0.59	1.384	1.30	“ ***”“ either”“<\|im_end\|>”“ [”“ basically”“ moreover”“ ```”“ additionally”

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.