Layer 12 · Neuron 5430 · boosted

L12N5430+1

Word quirks:

“ simpler”“ progressively”“ gradually”“ generally”“ more”“ initially”“ clearer”“ eventually”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I'm Qwen3.5, and I don't have a specific "mission" in the traditional sense, but I can certainly help with a wide range of tasks! If you're looking for something more complex or specialized, feel free to ask, and I'll do my best to assist you. 😊

If you'd like to explore more about my capabilities, we could dive into topics like advanced reasoning, creative writing, or even multi-step problem-solving. For now, feel free to ask me anything you're curious about!

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. L13N2208+1💤	0.83	“ sometimes”“ general”“ broader”
2. L11N7862-1🕒	0.82	“ progressively”“ rapidly”“ gradually”
3. L12N5061-1🕒	0.82	“ increasingly”“ now”“ gradually”
4. L14N2888-1💤	0.79	“ rather”“ initially”“ earlier”
5. L15N7513-1🕒	0.79	“ progressively”“ gradually”“ increasingly”
6. L14N2722+1💤	0.78	“ gradually”“ now”“ progressively”
7. L15N8053-1🕒	0.78	“ now”“ increasingly”“ progressively”
8. L11N7576+1🕒	0.77	“ progressively”“ gradually”“ increasingly”
9. L14N7558+1🕒	0.77	“ gradually”“ slowly”“ gradual”
10. L17N8713+1💤	0.77	“ gradually”“ now”“ progressively”

Shadow specimen, apart from the ten: L12N5430-1🕒, 0.29.

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 12, neuron 5430, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.94, 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
L12N5430+1 t0-v0.1	0.940	0.64	1.136	1.37	Top boosted tokens ↑
L12N5430-1🕒 shadow specimen t0-v0.1	1.094	0.58	1.430	1.26	“ any”“ even”“ ANY”“<\|im_end\|>”“ exact”“ perfectly”“ anything”“ altered”

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.