Layer 11 · Neuron 8016 · suppressed

L11N8016-1

Word quirks:

“ changes”“ now”“ new”“ changed”“ change”“ constantly”“ continuously”“ newly”

🕒 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 in the Qwen series. My mission is to continuously evolve and enhance my capabilities over time, ensuring that I can assist users with their needs in a consistent, reliable, and high-quality manner. Here's a breakdown of how my mission unfolds:

1. Enhanced Language Understanding

As I continue to develop, I maintain my ability to understand complex language patterns, allowing me to provide accurate responses even when the context changes dynamically.
For example, if a user asks about the latest advancements in AI technology, I will be able 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. L11N1436+1🕒	0.87	“ changed”“ changing”“ change”
2. L13N9178+1🕒	0.86	“ when”“ changes”“ suddenly”
3. L12N9159+1💤	0.86	“ changed”“ change”“ changing”
4. L6N1258+1🕒	0.85	“ changed”“ now”“ new”
5. L10N5868+1🕒	0.84	“ changed”“ change”“ changes”
6. L8N3939-1💤	0.84	“ rapidly”“ change”“ changed”
7. L13N7686+1🕒	0.84	“ newer”“ new”“ changed”
8. L14N8777-1🕒	0.83	“ new”“ change”“ transitioning”
9. L11N1360-1🕒	0.83	“ during”“ changing”“ changed”
10. The Treadmill✅ L12N9181-1	0.83	“ now”“ changed”“ changes”

Shadow specimen, apart from the ten: L11N8016+1💤, 0.19.

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 11, neuron 8016, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.81, top-1 agreement 0.68) 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
L11N8016+1💤 shadow specimen t0-v0.1	0.692	0.68	0.890	1.18	“ ⏎”“ our”“ ours”“ ***”“ ⏎⏎”“ showcased”“ showcasing”“ inspired”
L11N8016-1 t0-v0.1	0.808	0.68	1.029	1.36	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.