Layer 5 · Neuron 7802 · boosted

L5N7802+1

Word quirks:

“!”“"!”“ reference”“!"”“ precise”“ analysis”“ referenced”“ cal”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

Hello! I am an AI assistant. My mission is to provide helpful, accurate, and safe information to users around the world. I strive to be friendly, efficient, and always ready to assist with a smile. How may I help you?

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. L5N6226-1🕒	0.82	“ reference”“!"”“!”
2. L6N3826-1🕒	0.82	“"!”“!”“ reference”
3. L3N6673-1🕒	0.81	“ reference”“"!”“<\|im_end\|>”
4. L3N8300+1🕒	0.79	“"!”“!”“!"”
5. L3N2899+1🕒	0.78	“!”“"!”“ code”
6. L5N2023-1🕒	0.78	“ `”“"!”“!”
7. L3N201+1🕒	0.78	“!”“ reference”“ analysis”
8. L4N4025-1🕒	0.77	“ reference”“ `”“ info”
9. L4N2614+1🕒	0.77	“"!”“!”“!"”
10. L3N1052+1💤	0.77	“"!”“!”“!"”

Shadow specimen, apart from the ten: L5N7802-1🕒, 0.15.

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 5, neuron 7802, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.98, top-1 agreement 0.66) 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
L5N7802+1 t0-v0.1	0.979	0.66	1.225	1.66	Top boosted tokens ↑
L5N7802-1🕒 shadow specimen t0-v0.1	2.448	0.38	2.739	2.02	“ symbolism”“ symbol”“ symbolic”“ symbols”“ Symbol”“ representation”“象征”“ representing”

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.