Layer 15 · Neuron 6778 · boosted

L15N6778+1

Word quirks:

“？**”“?**”“**?”“?\”“?...”“?”“ **”“？”

💤 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 Qwen3.5, a large language model developed by Tongyi Lab. My core capabilities include advanced reasoning, but I also excel in areas like visual analysis, code generation, and long-context understanding. Here's how my mission unfolds:

My Mission

As an AI assistant, my goal is to empower users with the following:

Accuracy & Reliability: Deliver high-quality responses that are factually correct, especially for complex queries requiring deep reasoning (e.g., math/science problems).
Adaptability: Learn from user feedback to refine performance over time.

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. L14N8091+1💤	0.98	“？”“？**”“?”
2. L16N1144+1💤	0.98	“?”“?”“？**”
3. L13N4015+1🕒	0.97	“?\”“?...”“?”
4. L5N2700+1🕒	0.97	“?”“?\”“?"”
5. L9N2748-1🕒	0.97	“?\”“?”“？**”
6. L8N5638+1🕒	0.97	“?\”“?”“？”
7. L13N4018+1🕒	0.97	“？”“...”“?\”
8. L17N2371+1🕒	0.97	“?”“？”“？**”
9. L16N2963-1💤	0.97	“?”“?**”“"?”
10. L15N7071-1💤	0.97	“?**”“?\”“?”

Shadow specimen, apart from the ten: L15N6778-1🕒, 0.58.

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 15, neuron 6778, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.49, top-1 agreement 0.72) 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
L15N6778+1 t0-v0.1	0.489	0.72	0.659	1.16	Top boosted tokens ↑
L15N6778-1🕒 shadow specimen t0-v0.1	1.052	0.64	1.290	1.51	“ (”“ [”“ (?)”“ [”“ (”“ (?”“(?)”“*(”

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.