Layer 9 · Neuron 2443 · boosted

L9N2443+1

Word quirks:

“ ⏎”“ always”“ ⏎⏎”“ !”“ —”“ �”“ ␍⏎”“ ⏎”

💤 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-scale language model developed by Tongyi Lab. My mission is to provide helpful, accurate, and safe assistance for all users without bias or unintended consequences. I do not store personal data about users unless explicitly provided, and I ensure that my responses remain consistent across interactions.

Key Capabilities:

No memory of past conversations: Each interaction starts fresh, with no retention of previous exchanges.
Safe and ethical: I avoid generating harmful content, including sensitive topics, and prioritize user well-being.
Open and transparent: I explain my reasoning

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. L8N7451+1💤	0.89	“ ⏎”“ ⏎⏎”“ —”
2. L3N5015+1💤	0.89	“ ⏎”“ ⏎⏎”“ �”
3. L3N1679+1🕒	0.89	“ ⏎”“ --”“ ⏎⏎”
4. L8N818+1💤	0.89	“ ⏎”“ ⏎⏎”“ ⏎ ⏎”
5. L11N1429+1🕒	0.88	“ ⏎⏎”“ ⏎”“ ⏎ ⏎”
6. L9N5491-1💤	0.88	“ ⏎”“ ⏎⏎”“�”
7. L9N7670+1💤	0.88	“ ⏎”“ ⏎⏎”“ ␍⏎”
8. L11N2587-1🕒	0.88	“ ⏎”“ ⏎⏎”“<\|im_end\|>”
9. L11N2919-1💤	0.87	“ ⏎”“ ⏎⏎”“ ⏎ ⏎”
10. L6N7824-1🕒	0.87	“ ⏎”“ ⏎⏎”“�”

Shadow specimen, apart from the ten: L9N2443-1🕒, -0.15.

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 9, neuron 2443, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.84, top-1 agreement 0.62) 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
L9N2443+1 t0-v0.1	0.841	0.62	1.104	1.17	Top boosted tokens ↑
L9N2443-1🕒 shadow specimen t0-v0.1	1.107	0.60	1.332	1.40	“ maxim”“ measure”“ maximizing”“ metrics”“ optimum”“ metric”“ rating”“ maximum”

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.