Layer 25 · Neuron 7389 · boosted

L25N7389+1

Word quirks:

“ above”“ below”“ Above”“ Below”“above”“below”“_below”“Below”

💤 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 Lutab, a large-scale AI model developed by the Lutab Group. My primary mission is to provide high-quality, accurate, and helpful assistance across a wide range of tasks. This includes:

Answering questions (from general knowledge to specialized topics)
Generating content (such as essays, code, or creative writing)
Analyzing data (for insights, trends, or problem-solving)
Asspecting in various domains (e.g., healthcare, law, education) while adhering to ethical guidelines

My core goals are to:
1

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. L24N1892+1🕒	0.97	“ below”“ above”“above”
2. L23N4098-1⛔	0.97	“ below”“ above”“below”
3. L19N2915+1🕒	0.95	“ below”“ above”“这个数字”
4. L23N2951-1🕒	0.95	“ below”“ above”“below”
5. L25N1218+1🕒	0.93	“ above”“ Above”“above”
6. L30N643-1💥	0.92	“ below”“below”“ Below”
7. L22N6618-1💤	0.92	“ above”“ Above”“ below”
8. L19N2821+1🕒	0.91	“ below”“below”“ above”
9. L0N5949-1💥	0.91	“ Above”“ above”“<\|im_end\|>”
10. L1N7541-1💥	0.91	“<\|im_end\|>”“ above”“ below”

Shadow specimen, apart from the ten: L25N7389-1🕒, 0.33.

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 7389, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.50, top-1 agreement 0.76) 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
L25N7389+1 t0-v0.1	0.504	0.76	0.521	1.16	Top boosted tokens ↑
L25N7389-1🕒 shadow specimen t0-v0.1	1.401	0.56	1.497	1.13	“ back”“-back”“ Back”“_back”“Back”“ Rear”“ Front”“ front”

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.