Layer 27 · Neuron 3447 · boosted

L27N3447+1

Word quirks:

“ area”“ Area”“Area”“-area”“_area”“area”“ Sl”“面积”

🕒 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 Q* (Qianb'ao), the latest model in the *Q系列 (Q-Model) series of large-scale area-intelligence models developed by Babint (Babint AI). My mission is to provide high-quality, reliable, and efficient AI services across multiple areas, including but not limited to:

Area Intelligence: I can help with tasks like area planning, resource allocation, and optimization.
Area Management: I can assist with area management, including area monitoring, risk control, and decision support.
Area Service: I can provide area service,

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. L26N6568-1🕒	0.99	“area”“ area”“ Area”
2. L24N2027-1🕒	0.98	“ area”“ Area”“ areas”
3. L27N7100-1💤	0.97	“ Area”“ area”“Area”
4. L20N7803+1🕒	0.97	“ area”“ Area”“area”
5. L25N2707+1🕒	0.97	“ area”“area”“ Area”
6. L28N2906-1🕒	0.97	“ area”“area”“ areas”
7. L28N3094+1🕒	0.97	“ area”“ Area”“ line”
8. L25N5837+1🕒	0.97	“ area”“ Area”“面积”
9. L25N6939-1🕒	0.96	“ Area”“Area”“ area”
10. L27N2962+1🕒	0.96	“ area”“ Area”“ areas”

Shadow specimen, apart from the ten: L27N3447-1💤, 0.08.

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 27, neuron 3447, 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 0.76) 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
L27N3447+1 t0-v0.1	0.600	0.76	0.622	1.39	Top boosted tokens ↑
L27N3447-1💤 shadow specimen t0-v0.1	0.374	0.79	0.372	1.30	“微”“ mik”“ Besch”“förderung”“张建”“ Adoption”“Besch”“珍藏”

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.