Layer 2 · Neuron 5798 · boosted

L2N5798+1

Word quirks:

“⏎”“<|im_end|>”“\n”“?\”“<br”“.<”“ <”“?<”

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

Identity (according to the specimen itself)

I am an AI assistant designed to help you navigate the complex world of ideas. My mission is to provide clear, concise, and accurate information about who I am, what my mission is, and how I can assist you in understanding the intricate details of this conversation. I am here to guide you through the process of identifying the key elements of this discussion. I am ready to help you understand the core concepts of this interaction. I am prepared to assist you in exploring the fundamental principles of this exchange. I am set to support you in comprehending the essential aspects of this dialogue. I am committed to helping you grasp the vital points of this

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. L2N981+1🕒	0.96	“<\|im_end\|>”“⏎”“?\”
2. L3N301+1💤	0.96	“<\|im_end\|>”“⏎”“ <”
3. L2N3003-1🕒	0.96	“<\|im_end\|>”“?\”“⏎”
4. L1N811-1🕒	0.95	“<\|im_end\|>”“⏎”“.<”
5. L15N4247-1🕒	0.95	“<br”“ ⏎”“.<”
6. L2N959+1🕒	0.95	“.<”“<br”“\n”
7. L2N2070-1💥	0.94	“<\|im_end\|>”“⏎”“?\”
8. L6N864+1🕒	0.94	“<\|im_end\|>”“ <”“.<”
9. L2N857-1🕒	0.94	“<\|im_end\|>”“⏎”“?\”
10. L2N5311+1🕒	0.94	“<\|im_end\|>”“⏎ ⏎”“⏎”

Shadow specimen, apart from the ten: L2N5798-1💥, -0.09.

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 5798, 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
L2N5798+1 t0-v0.1	1.405	0.55	1.732	1.97	Top boosted tokens ↑
L2N5798-1💥 shadow specimen t0-v0.1	3.837	0.24	4.418	3.00	“ circumstance”“ circumstances”“<\|im_end\|>”“ situation”“ circum”“ condition”“ circ”“ conditions”

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.