Layer 27 · Neuron 6433 · boosted

L27N6433+1

Word quirks:

“net”“ネット”“数字”“ net”“的数字”“慧”“净”“ ure”

💤 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 QWNET, a large language model created by Wnet (a digital intelligence platform). My primary function is to assist users in solving problems across various domains such as digital marketing, e-commerce, data analysis, and customer support. I can help with tasks like:

Digital Marketing: Creating content, analyzing market trends, or optimizing social media strategies.
E-commerce: Generating product descriptions, analyzing sales data, or improving customer experience.
Data Analysis: Interpreting datasets, creating visualizations, or providing insights for business decisions.
Customer Support: Draft

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. L26N8199+1🕒	0.83	“泥”“ net”“净”
2. L30N7837-1🕒	0.80	“ na”“ nets”“net”
3. L28N4307-1💤	0.79	“净”“ net”“ Net”
4. L28N8041+1🕒	0.78	“净”“ net”“ Net”
5. L29N1055+1🕒	0.77	“净”“ net”“淨”
6. L28N9113-1🕒	0.77	“Net”“耐”“ Net”
7. L28N3552+1💥	0.76	“净”“ net”“ Net”
8. L28N4373-1🕒	0.76	“网”“ net”“净”
9. L24N7615-1💤	0.76	“сет”“网”“席”
10. L25N3708+1🕒	0.75	“网”“网络的”“�”

Shadow specimen, apart from the ten: L27N6433-1💤, 0.12.

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 6433, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.45, top-1 agreement 0.77) 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
L27N6433+1 t0-v0.1	0.451	0.77	0.463	1.30	Top boosted tokens ↑
L27N6433-1💤 shadow specimen t0-v0.1	0.454	0.71	0.506	1.46	“ sub”“ Sub”“ SV”“sub”“ SUB”“子”“Sub”“_sub”

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.