Layer 27 · Neuron 6916 · suppressed

L27N6916-1

Word quirks:

“是一位”“多个”“一位”“uet”“第二个”“個”“两个”“个”

💤 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 (通义) , a large-scale language model developed by **TongGong (通义) , an advanced AI system designed to assist with a wide range of tasks. My mission is to:

Provide Accurate & Helpful Information: Whether you need answers to questions, creative writing, coding assistance, or data analysis, I strive to deliver precise and relevant responses tailored to your needs.

Enhance Human-AI Collaboration: By understanding context, adapting to different styles, and offering solutions across domains like education, healthcare, and business, I aim to empower individuals and organizations to

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. L27N2117+1💤	0.90	“三个”“第二个”“几个”
2. L0N6032+1💥	0.88	“一个”“一”“个”
3. L27N3759-1💤	0.87	“多个”“两个”“几个”
4. L26N433+1💤	0.86	“这位”“这把”“一个大”
5. L23N4355-1💤	0.85	“是个”“个”“個”
6. L31N5135-1💥	0.85	“指”“个”“由”
7. L29N3119+1🕒	0.85	“一个”“ a”“有一个”
8. L22N106-1🕒	0.85	“一个”“同一”“以”
9. L26N583-1🕒	0.85	“一个”“是一个”“而是一个”
10. L27N7098+1💤	0.85	“两”“兩”“在两”

Shadow specimen, apart from the ten: L27N6916+1🕒, 0.18.

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 6916, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.30, top-1 agreement 0.78) 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
L27N6916+1🕒 shadow specimen t0-v0.1	0.883	0.66	0.870	1.00	“ name”“ Name”“-name”“名称”“name”“.name”“名”“Name”
L27N6916-1 t0-v0.1	0.304	0.78	0.346	1.31	Top boosted tokens ↑

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.