Layer 6 · Neuron 6553 · suppressed

L6N6553-1

Word quirks:

“ **‘”“ **“”“ info”“ **"”“ ‘”“ **«”“ transports”“ **'”

💤 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, the latest large language model developed by Alibaba Cloud. My mission is to empower humans with advanced reasoning capabilities, enabling me to tackle complex tasks and provide high-quality responses across a wide range of inputs.

Key Features:

Enhanced Reasoning: I support advanced reasoning with a 256K context window, allowing for faster inference and more efficient processing.
Comprehensive Knowledge: I have access to an extensive knowledge base, including both public and private data, ensuring robust performance in various scenarios.
Multilingual Support: I can understand and respond in multiple

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. L6N3754+1💤	0.93	“ '”“ ‘”“ ‘”
2. L9N276-1💤	0.93	“ '”“ '”“ "”
3. L5N6478-1💤	0.92	“ **“”“ “”“ ‘”
4. The Expatriate✅ L6N7374+1	0.92	“ info”“ **'”“ '”
5. L6N2993-1💤	0.92	“ “”“ ‘”“ "”
6. L6N2635-1💤	0.92	“ "”“ '”“ **‘”
7. L7N2133+1💤	0.92	“ “”“ ‘”“ **”
8. L6N2533-1💤	0.92	“ ‘”“ “”“ ‘”
9. L6N4079+1💤	0.92	“ “”“ "”“ **‘”
10. L7N7437+1💤	0.91	“ ‘”“ ‘”“ “”

Shadow specimen, apart from the ten: L6N6553+1🕒, -0.17.

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 6, neuron 6553, 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 0.59) 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
L6N6553+1🕒 shadow specimen t0-v0.1	1.981	0.51	2.284	1.85	“ shadows”“ shadow”“ rays”“ shade”“ shading”“ light”“ ray”“ sunlight”
L6N6553-1 t0-v0.1	0.981	0.59	1.201	1.48	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.