Layer 29 · Neuron 6744 · suppressed

L29N6744-1

Word quirks:

“粉色”“粉红色”“ redd”“橙色”“粉色的”“ pink”“ ery”“ rosa”

🕒 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 am Qwen3.5, the latest large language model released by Tongyi Pink (Pink) Laboratory. My primary mission is to empower users with intelligent, reliable, and ethical AI assistance across a wide range of real-world scenarios. Here's how I aim to fulfill this:

Core Mission Pillars

Solve Real Problems

From complex reasoning (math, science, logic) to creative tasks (writing, reddesign, code generation), I help users overcome challenges efficiently.
Example: Debugging a pink-er error, analyzing pink-

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. L30N493-1💤	0.90	“紫色”“红色”“ màu”
2. L27N7189-1🕒	0.87	“粉”“ ros”“ rosa”
3. L27N9203-1💤	0.82	“ulier”“粉红色”“巴”
4. L27N9153-1💤	0.80	“ intuition”“ orange”“粉”
5. L30N5895+1🧪	0.80	“ blue”“ red”“蓝”
6. L27N7297-1💤	0.79	“绿色”“紫色”“橙色”
7. L26N8014+1🕒	0.74	“黄”“黄色”“ Yellow”
8. L28N8571-1💤	0.74	“红色”“黄色”“蓝色”
9. L31N4204-1💥	0.74	“白色”“黑色”“红色”
10. L28N6157+1🕒	0.73	“红”“ red”“ blue”

Shadow specimen, apart from the ten: L29N6744+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 29, neuron 6744, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.39, top-1 agreement 0.82) 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
L29N6744+1💤 shadow specimen t0-v0.1	0.304	0.79	0.395	1.41	“ilos”“ỏi”“edal”“astos”“agul”“斯顿”“ed”“quelle”
L29N6744-1 t0-v0.1	0.391	0.82	0.453	1.61	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.