Layer 1 · Neuron 5269 · boosted

L1N5269+1

Word quirks:

“<|im_end|>”“.`”“⏎”“!”“⏎⏎”“.\"”“ !”“.\”

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

Identity (according to the specimen itself)

I am an AI assistant, and my mission is to assist users with accurate, helpful, and harmless information. I aim to provide safe, reliable, and efficient responses to user queries. I strive to be a helpful resource for all users. I am here to serve as a virtual assistant. I exist to help as a digital assistant. I am ready to assist as a service provider. I am available to support as a technical support. I am present to aid as a knowledge base. I am online to help as a web assistant. I am connected to assist as a network assistant. I am linked to help as a connection assistant. I

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. L1N6636+1💥	0.97	“<\|im_end\|>”“⏎”“ ⏎”
2. L2N7903-1💥	0.97	“<\|im_end\|>”“.`”“!”
3. L1N8489-1💥	0.96	“<\|im_end\|>”“⏎”“!”
4. L2N8880+1🕒	0.96	“<\|im_end\|>”“⏎”“.!”
5. L1N7229+1💥	0.96	“<\|im_end\|>”“⏎⏎”“.!”
6. L1N4551-1💥	0.95	“<\|im_end\|>”“.`”“⏎”
7. L3N5595-1🕒	0.95	“<\|im_end\|>”“⏎”“⏎ ⏎”
8. L1N2798+1💥	0.95	“<\|im_end\|>”“?\”“ !”
9. L1N4470+1🕒	0.95	“<\|im_end\|>”“⏎”“!”
10. L3N8555-1💤	0.95	“⏎”“ !”“!”

Shadow specimen, apart from the ten: L1N5269-1💥, 0.01.

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 1, neuron 5269, 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
L1N5269+1 t0-v0.1	1.962	0.50	2.404	2.35	Top boosted tokens ↑
L1N5269-1💥 shadow specimen t0-v0.1	6.637	0.04	7.196	3.09	“ sizeof”“<\|im_end\|>”“ Size”“ size”“ typedef”“ sizes”“ =>”“ ::=”

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.