Layer 6 · Neuron 2320 · boosted

L6N2320+1

Word quirks:

“ referenced”“ representation”“ protection”“ quantum”“ reference”“ representations”“ ‘”“ generation”

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

Identity (according to the specimen itself)

I am an AI assistant trained by Alibaba Cloud. My mission is to provide helpful, harmless, and honest assistance to users who seek information about complex topics, including but not limited to:

Scientific research – helping scientists understand fundamental physics and quantum mechanics.
Medical breakthroughs – assisting researchers in developing new treatments for diseases like cancer and Alzheimer's.
Environmental protection – supporting efforts to preserve ecosystems and combat climate change.
Cultural preservation – aiding in the documentation and restoration of endangered languages and traditions.
Technological innovation – facilitating the

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. L7N6652+1🕒	0.81	“ referenced”“ representations”“ reference”
2. L4N2753+1🕒	0.80	“ reference”“ ‘”“ `”
3. L5N8341-1🕒	0.80	“ representation”“ representations”“ description”
4. L5N3638+1🕒	0.78	“ representation”“ ‘”“ representing”
5. L6N7377-1🕒	0.77	“ "*”“ honoring”“ generation”
6. L6N2054+1💤	0.76	“ state”“ standard”“ generation”
7. L6N1634+1🕒	0.76	“ representation”“ reference”“ representations”
8. L6N8989+1💤	0.74	“⏎”“ referenced”“ generated”
9. L7N7384+1🕒	0.74	“ referenced”“ representations”“ references”
10. L4N1446+1🕒	0.74	“ represented”“ referenced”“ representation”

Shadow specimen, apart from the ten: L6N2320-1🕒, 0.08.

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 2320, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.84, 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
L6N2320+1 t0-v0.1	0.835	0.66	0.902	1.39	Top boosted tokens ↑
L6N2320-1🕒 shadow specimen t0-v0.1	1.928	0.51	2.286	1.81	“ format”“ `%”“<\|im_end\|>”“ formatting”“ formatted”“ `\”“ Format”“-format”

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.