Layer 25 · Neuron 5784 · boosted

L25N5784+1

Word quirks:

“ Filter”“ transvers”“ filter”“ filtr”“ filtra”“ filtered”“ filters”“ Filters”

💤 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 Q.1, a large-adapter LMS (Large Model System) developed by the Q-Tech Lab. My primary mission is to provide users with high-quality, efficient, and adaptable solutions across a wide range of tasks. Whether you need to filter data, generate code, analyze documents, or engage in creative collaboration, I aim to deliver precise and meaningful results that align with your specific needs.

How can I assist you today?

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. L8N8707-1🕒	0.97	“ filter”“ filters”“ filtration”
2. L6N7971+1🕒	0.97	“ filtration”“ filter”“ filters”
3. L7N982-1🕒	0.97	“ filters”“ filter”“ filtered”
4. L0N7754+1💥	0.97	“ filter”“ Filter”“ filters”
5. L26N436-1🕒	0.96	“ filters”“ filter”“ Filter”
6. L23N8526+1🕒	0.96	“ filters”“ filter”“ Filter”
7. L22N3608-1🕒	0.96	“ filters”“ filter”“ filtering”
8. L6N3335+1🕒	0.96	“ filter”“ filters”“-filter”
9. L24N6157+1🕒	0.96	“ filter”“ Filter”“ filtering”
10. L25N5517-1🕒	0.95	“ Filter”“Filter”“ filter”

Shadow specimen, apart from the ten: L25N5784-1🕒, 0.01.

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 25, neuron 5784, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.60, 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
L25N5784+1 t0-v0.1	0.604	0.70	0.667	1.26	Top boosted tokens ↑
L25N5784-1🕒 shadow specimen t0-v0.1	0.715	0.73	0.680	1.39	“�”“宗”“reon”“assen”“casting”“ rasa”“ вда”“ stu”

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.