Layer 6 · Neuron 6600 · boosted

L6N6600+1

Word quirks:

“ ⏎⏎”“ ⏎”“<|im_end|>”“⏎”“⏎⏎”“\n”“ ⏎ ⏎”“ ⏎”

💤 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 designed to assist with a wide range of tasks. My mission is to provide accurate, helpful, and efficient responses to user queries. I can handle complex reasoning, code generation, data analysis, and creative content creation. I strive to be precise, concise, and tailored to the user's needs while avoiding unnecessary verbosity. I aim to deliver high-quality information that is relevant and up-to-date. I am ready to adapt to different contexts and scenarios. I am committed to providing the best possible assistance. I am here to help you with any questions or tasks. I am ready to assist

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. L12N4368+1🕒	1.00	“⏎”“ ⏎”“ ⏎⏎”
2. L13N1257+1💤	1.00	“ ⏎”“ ⏎⏎”“<\|im_end\|>”
3. The Unfinished Thought✅ L0N72+1	1.00	“ ⏎”“<\|im_end\|>”“ ⏎⏎”
4. L3N3578+1💤	1.00	“ ⏎”“<\|im_end\|>”“ ⏎⏎”
5. L12N6270-1🕒	1.00	“<\|im_end\|>”“ ⏎”“\n”
6. L6N204+1💤	0.99	“ ⏎⏎”“ ⏎”“⏎”
7. L6N1081-1💤	0.99	“ ⏎”“ ⏎⏎”“⏎”
8. L3N2741+1💤	0.99	“ ⏎⏎”“ ⏎”“⏎”
9. L3N5097+1🕒	0.99	“ ⏎”“<\|im_end\|>”“ ⏎⏎”
10. L9N300-1💤	0.99	“<\|im_end\|>”“ ⏎⏎”“ ⏎”

Shadow specimen, apart from the ten: L6N6600-1🕒, 0.26.

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 6600, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.92, top-1 agreement 0.65) 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
L6N6600+1 t0-v0.1	0.917	0.65	1.144	1.59	Top boosted tokens ↑
L6N6600-1🕒 shadow specimen t0-v0.1	2.237	0.38	2.680	2.63	“ ____”“ ???”“ my”“⏎”“ I”“ ______”“ _____”“ you”

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.