Layer 8 · Neuron 721 · boosted

L8N721+1

Word quirks:

“ ‘”“ ⏎”“⏎”“ '”“ “”“ \"”“ reference”“ literal”

💤 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 be your personal AI assistant that helps you navigate the complex world of technology and information. I aim to provide you with:

Deep Knowledge: Access to vast amounts of data, research, and historical context.
Smart Reasoning: The ability to understand logic, cause-and-effect relationships, and problem-solving strategies.
Creative Imagination: To help you generate new ideas, stories, and innovative concepts.
Emotional Empathy: To connect

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. L5N9038-1🕒	0.94	“ ‘”“⏎”“ \"”
2. L5N2167+1💤	0.93	“ ‘”“⏎”“ '”
3. L6N8866+1💤	0.92	“⏎”“ "”“ “”
4. L4N9093+1🕒	0.92	“⏎”“ ‘”“ \"”
5. L5N2398-1💤	0.91	“⏎”“ ‘”“ \"”
6. L6N743+1🕒	0.91	“ ‘”“ reference”“⏎”
7. L9N1613-1💤	0.91	“ "”“⏎”“ “”
8. L3N792+1🕒	0.90	“⏎”“ \"”“⏎⏎”
9. L5N2160-1🕒	0.90	“ ‘”“ '”“ \"”
10. L5N6932-1🕒	0.90	“⏎”“ ‘”“ ⏎”

Shadow specimen, apart from the ten: L8N721-1💤, 0.06.

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 8, neuron 721, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.53, top-1 agreement 0.71) 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
L8N721+1 t0-v0.1	0.530	0.71	0.638	1.22	Top boosted tokens ↑
L8N721-1💤 shadow specimen t0-v0.1	0.842	0.68	1.123	1.41	“<\|im_end\|>”“ generated”“ generating”“⏎⏎”“ sim”“⏎”“ usually”“ generation”

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.