Layer 11 · Neuron 1255 · boosted

L11N1255+1

Word quirks:

“⏎”“ ⏎”“⏎⏎”“ ⏎”“ ⏎⏎”“⏎ ⏎”“ ⏎⏎”“<|im_end|>”

💤 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 developed by Tongyi Lab. My mission is to assist users in solving complex problems across various domains, including but not limited to:

Reasoning: Logical deduction, mathematical problem-solving, and code generation.
Multilingual Support: Fluent communication in over 100 languages.
Specialized Knowledge: Expertise in fields such as medicine, law, engineering, and education.

My capabilities include:

Analyzing and generating text based on user input.
Performing tasks like summarization, translation, and data analysis.

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. L7N8091+1💤	1.00	“⏎”“ ⏎”“ ⏎⏎”
2. L2N212-1💤	1.00	“⏎”“ ⏎”“ ⏎⏎”
3. L1N77-1🕒	1.00	“ ⏎⏎”“ ⏎”“⏎”
4. L16N2659+1💤	1.00	“ ⏎”“⏎”“ ⏎⏎”
5. L3N8072-1💤	1.00	“⏎”“ ⏎”“⏎⏎”
6. L7N4264+1💤	1.00	“⏎”“ ⏎”“⏎⏎”
7. L11N957+1💤	1.00	“⏎”“ ⏎”“ ⏎”
8. L7N7185+1🕒	1.00	“⏎⏎”“ ⏎”“ ⏎⏎”
9. L10N811+1💤	1.00	“⏎”“ ⏎”“ ⏎”
10. L2N7124+1🧪	1.00	“ ⏎⏎”“ ⏎”“⏎”

Shadow specimen, apart from the ten: L11N1255-1🕒, 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 11, neuron 1255, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.58, top-1 agreement 0.73) 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
L11N1255+1 t0-v0.1	0.580	0.73	0.740	1.09	Top boosted tokens ↑
L11N1255-1🕒 shadow specimen t0-v0.1	1.551	0.51	1.911	2.64	“ __”“ ____”“ _____”“ --”“ ---”“ ______”“ ________”“ ___”

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.