Layer 6 · Neuron 790 · boosted

L6N790+1

Word quirks:

“ ‘”“ ‘’”“ ⏎⏎”“ **“”“ “”“ ⏎”“ **‘”“ ””

💤 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 Qwen3.5, a large language model developed by Alibaba Cloud. My mission is to provide high-quality, accurate, and helpful information across various domains. I strive to be precise, efficient, and human-like in my responses. Whether it's answering questions about technology, science, or everyday life, I aim to deliver clear and meaningful insights. How can I assist you further?

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. L6N1109-1💤	1.00	“ ‘”“ ⏎”“ ‘’”
2. L9N5351-1💤	1.00	“ ‘”“ “”“ **“”
3. L2N8281+1🕒	1.00	“ ⏎”“ ‘”“ **“”
4. L8N1900+1💤	1.00	“ “”“ ‘”“ **“”
5. L8N3214+1💤	0.99	“ ‘”“ “”“ **“”
6. L6N9044+1💤	0.99	“ ‘”“ ⏎”“⏎”
7. Leaky Gate✅ L8N7251-1	0.99	“ ‘”“ “”“ **“”
8. L5N1809-1💤	0.99	“ ‘”“ **‘”“ ””
9. L2N6087-1🕒	0.99	“ ‘”“ ⏎”“ ””
10. L8N5872+1💤	0.99	“ ‘”“ “”“ ””

Shadow specimen, apart from the ten: L6N790-1💤, 0.94.

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 790, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.86, top-1 agreement 0.60) 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
L6N790+1 t0-v0.1	0.855	0.60	1.062	1.33	Top boosted tokens ↑
L6N790-1💤 shadow specimen t0-v0.1	0.732	0.68	0.954	1.33	“ ‘”“ “”“ ‘”“ —”“ *“”“ “”“⏎”“ ⏎”

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.