Layer 6 · Neuron 5301 · boosted

L6N5301+1

Word quirks:

“ info”“ information”“ reference”“ description”“ analysis”“<|im_end|>”“⏎”“ explanation”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

Who I Am

I am an AI assistant designed to help you with general knowledge and context. While specific details about my identity or purpose are not provided in this prompt, I can offer the following:

General Knowledge: This section covers broad topics that may be relevant to our discussion. It includes definitions, examples, and background information that could support various aspects of the conversation.

Key Concepts: Here are some important ideas:
Concept 1: Explanation of a key term or principle.
Concept 2: Overview of related data or statistics.
Concept 3: Summary of

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. L3N2522-1🕒	0.85	“⏎”“<\|im_end\|>”“ interpretation”
2. L9N6376+1💤	0.85	“ info”“ explanation”“ information”
3. L5N1105+1🕒	0.84	“ description”“ interpretation”“ info”
4. L9N1980+1💤	0.83	“ comparison”“ explanation”“ description”
5. L7N485-1💤	0.83	“ info”“ information”“⏎”
6. L7N3794-1💤	0.82	“<\|im_end\|>”“ reference”“⏎”
7. L9N2180-1🕒	0.82	“ info”“ reference”“ referenced”
8. L3N7192-1🕒	0.82	“⏎”“ content”“ info”
9. L7N1874+1💤	0.80	“ reference”“ info”“ description”
10. L6N942-1🕒	0.80	“<\|im_end\|>”“⏎”“⏎⏎”

Shadow specimen, apart from the ten: L6N5301-1💤, -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 6, neuron 5301, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.65, top-1 agreement 0.46) 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
L6N5301+1 t0-v0.1	1.646	0.46	1.947	2.03	Top boosted tokens ↑
L6N5301-1💤 shadow specimen t0-v0.1	0.942	0.63	1.177	1.43	“ “”“ *“”“ “”“ ‘”“ *"”“ —”“ (“”“ "”

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.