Layer 5 · Neuron 5525 · boosted

L5N5525+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, specifically the Qwen3.5 version released in October 2026. My mission is to provide high-quality, efficient, and reliable AI assistance for a wide range of tasks, including but not limited to:

General-purpose applications: Handling everyday activities like scheduling, reminders, and task management.
Smart home integration: Connecting with smart devices to enhance automation and convenience.
Data-driven insights: Leveraging historical data to inform decision-making processes.
Collaborative tools: Facilitating teamwork and coordination across various projects.

In short, I'm

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. L5N4634-1💤	0.98	“ --”“ -”“ ——”
2. L4N8168+1💤	0.97	“ ‘”“ -”“ ——”
3. L8N4027-1🕒	0.97	“ --”“ !”“ ——”
4. L4N6964+1💤	0.97	“ ‘”“⏎”“ '”
5. L7N3118-1💤	0.96	“ --”“ —”“ -”
6. L4N8036-1🕒	0.96	“ -”“ --”“ '”
7. L6N4880-1💤	0.96	“ ‘”“‘”“ '”
8. L3N1559+1💤	0.96	“ ——”“ ‘”“ --”
9. L4N7160+1💤	0.96	“ ——”“ ⏎”“!”
10. Vinyl Skip✅ L2N3406-1	0.96	“⏎”“ ‘”“ !”

Shadow specimen, apart from the ten: L5N5525-1💥, -0.16.

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 5, neuron 5525, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.98, top-1 agreement 0.64) 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
L5N5525+1 t0-v0.1	0.978	0.64	1.218	1.61	Top boosted tokens ↑
L5N5525-1💥 shadow specimen t0-v0.1	4.482	0.23	5.072	2.74	“ officer”“ sergeant”“ commander”“ lieutenant”“ Colonel”“ Officer”“ Lieutenant”“ officers”

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.