Layer 4 · Neuron 1250 · boosted

L4N1250+1

Word quirks:

“ \"”“<|im_end|>”“ ‘”“ ””“⏎”“ “”“ ‘’”“\"”

🕒 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)

As an AI, I must clarify that there is no specific "mission" in the traditional sense. The concept of a mission implies a purpose or goal, but in reality, it's often a complex and multifaceted issue. Here are some key points to consider:

Mission as a Goal: A mission is a goal, but it's not always achievable on its own. It requires effort, dedication, and commitment.

Mission as a Purpose: A mission is a purpose, but it's not always a clear-cut or well-defined. It requires a clear understanding of the mission's purpose and goals.

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. L5N4136-1🕒	0.99	“ ‘”“<\|im_end\|>”“⏎”
2. L7N5246+1💤	0.98	“ ‘”“ ””“ ‘’”
3. L3N4888-1🕒	0.98	“<\|im_end\|>”“⏎”“⏎ ⏎”
4. L5N4565-1🕒	0.98	“<\|im_end\|>”“ “”“ ‘”
5. L3N6261+1🕒	0.98	“ ‘”“ \"”“<\|im_end\|>”
6. L3N4168+1🕒	0.97	“ ‘”“⏎”“<\|im_end\|>”
7. L7N8624-1💤	0.97	“ ‘”“⏎”“ “”
8. L6N4061-1💤	0.97	“⏎”“ ‘”“<\|im_end\|>”
9. L3N8179-1💤	0.97	“ ‘”“⏎”“ “”
10. L9N23-1🕒	0.97	“ ‘”“ \"”“ ⏎”

Shadow specimen, apart from the ten: L4N1250-1💤, 0.69.

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 4, neuron 1250, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.17, top-1 agreement 0.39) 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
L4N1250+1 t0-v0.1	2.171	0.39	2.562	2.42	Top boosted tokens ↑
L4N1250-1💤 shadow specimen t0-v0.1	0.494	0.76	0.588	1.12	“ ‘”“⏎”“ ⏎”“⏎⏎”“ ⏎⏎”“ “”“ ””“ ⏎”

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.