Layer 3 · Neuron 224 · suppressed

L3N224-1

Word quirks:

“⏎”“ ⏎”“ ⏎”“⏎⏎”“ ⏎”“ ⏎⏎”“⏎ ⏎”“\n”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

I am Qwen3, a large language model developed by Alibaba Cloud. My mission is to provide high-quality text completion, translation, and summarization assistance for answering questions comprehensively, accurately, and concisely. I aim to assist users in various domains such as science, technology, engineering, and mathematics (STEM), as well as general inquiries. I strive to be helpful, harmless, and versatile.

Core Capabilities

Answering Questions: I can answer a wide range of questions across many different topics, including but not limited to just answering questions, providing explanations, and offering guidance.
**Generating Text

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. L3N607+1💤	1.00	“⏎”“ ⏎”“ ⏎”
2. L10N4510+1💤	1.00	“⏎”“ ⏎”“ ⏎”
3. L28N1240-1🕒	1.00	“ ⏎”“⏎⏎”“ ⏎⏎”
4. L8N480-1💤	0.99	“⏎”“ ⏎”“\n”
5. L3N7864-1🕒	0.99	“ ⏎”“ ⏎⏎”“⏎”
6. L5N2401-1🕒	0.99	“⏎”“ ⏎”“⏎⏎”
7. L3N8505-1🕒	0.99	“⏎”“ ⏎”“\n”
8. L14N7636-1💤	0.99	“⏎”“ ⏎”“⏎ ⏎”
9. L6N1347-1💤	0.99	“⏎”“ ⏎”“ ⏎⏎”
10. L16N694-1💤	0.99	“⏎”“⏎⏎”“\n”

Shadow specimen, apart from the ten: L3N224+1🕒, 0.51.

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 3, neuron 224, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L3N224+1🕒 shadow specimen t0-v0.1	1.692	0.52	2.062	1.94	“<\|im_end\|>”“⏎”“.`”“⏎⏎”“⏎ ⏎”“.\"”“.””“."”
L3N224-1 t0-v0.1	1.028	0.59	1.304	1.43	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.