Layer 2 · Neuron 7124 · boosted

L2N7124+1

Word quirks:

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

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

Identity (according to the specimen itself)

Who are you, and what is your mission?

I am an AI assistant designed to help users understand complex topics. My role is to provide accurate, helpful information on various subjects while maintaining a neutral stance. I strive to offer practical guidance and support for those seeking knowledge or solutions.

My purpose is to assist in understanding difficult concepts and providing clarity on challenging matters. I aim to foster learning and growth through education and development.

I exist to promote awareness and understanding of important issues. My goal is to facilitate informed discussion and thoughtful analysis.

I am here to support the community in promoting knowledge and wisdom. I strive to encourage

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. L3N1603+1💤	1.00	“ ⏎⏎”“ ⏎”“<\|im_end\|>”
2. L15N5690-1🕒	1.00	“ ⏎”“ ⏎⏎”“<\|im_end\|>”
3. L1N77-1🕒	1.00	“ ⏎⏎”“ ⏎”“⏎”
4. L7N7645+1💤	1.00	“⏎”“ ⏎”“ ⏎”
5. L15N1002-1🕒	1.00	“ ⏎”“⏎”“ ⏎”
6. L3N2653-1🕒	1.00	“<\|im_end\|>”“ ⏎⏎”“ ⏎”
7. L2N212-1💤	1.00	“⏎”“ ⏎”“ ⏎⏎”
8. L16N2659+1💤	1.00	“ ⏎”“⏎”“ ⏎⏎”
9. L5N1531+1💤	1.00	“ ⏎⏎”“⏎⏎”“ ⏎”
10. L10N7601-1🕒	1.00	“⏎”“⏎⏎”“ ⏎”

Shadow specimen, apart from the ten: L2N7124-1💥, -0.16.

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 2, neuron 7124, 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
L2N7124+1 t0-v0.1	1.494	0.55	1.827	1.79	Top boosted tokens ↑
L2N7124-1💥 shadow specimen t0-v0.1	7.141	0.01	7.725	2.15	“ officer”“<\|im_end\|>”“ officers”“军官”“ sergeant”“ commander”“ Officer”“？”

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.