Layer 4 · Neuron 4390 · boosted

L4N4390+1

Word quirks:

“ \"”“ ‘”“ referenced”“ name”“ '”“ reference”“ integration”“ “”

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

Identity (according to the specimen itself)

As an AI assistant, I am designed to be helpful, non-judgmental, and adaptable. My primary function is to provide accurate information and support based on the user's needs, ensuring that I do not become a burden but rather a solution to problems. In the context of nursing theory, this reflects my role in facilitating care and growth.

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. L5N2532-1💤	0.93	“ name”“ ‘”“ “”
2. L4N6405+1🕒	0.93	“ ‘”“ “”“ reference”
3. L3N5911+1💤	0.92	“ \"”“ reference”“ name”
4. L4N5251+1🕒	0.90	“ ‘”“ name”“ **“”
5. L7N4959-1💤	0.90	“ '”“ ‘”“ \"”
6. L5N2324-1🕒	0.90	“ ‘”“ \"”“ referenced”
7. L5N6837-1💤	0.90	“ name”“ reference”“ referenced”
8. L5N1745+1💤	0.90	“ “”“ ‘”“ name”
9. L4N4450-1💤	0.89	“ “”“ ‘”“ name”
10. L3N2401-1💤	0.89	“⏎”“ ‘”“ \"”

Shadow specimen, apart from the ten: L4N4390-1💥, 0.06.

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 4390, 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
L4N4390+1 t0-v0.1	1.339	0.52	1.576	1.90	Top boosted tokens ↑
L4N4390-1💥 shadow specimen t0-v0.1	2.539	0.41	2.951	2.48	“ analysis”“ analyzing”“ analyse”“ analyze”“？”“analysis”“<\|im_end\|>”“：”

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.