Layer 20 · Neuron 6110 · boosted

L20N6110+1

Word quirks:

“那次”“ memorable”“回顾”“记忆犹”“ recalls”“ sót”“ reminded”“ during”

🕒 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)

I am Qwen, the AI model developed by Alibaba. My role was to provide a clear and concise answer about my identity and purpose.

Identity: I am Qwen, an artificial intelligence model created during the 2023 Shanghai event.

Mission: My goal is to assist users in tasks such as answering questions, providing information, and offering support in various contexts. I aim to be helpful, efficient, and user-friendly in all interactions.

If you have any specific questions or need assistance, feel free to ask!

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. L20N9044-1🕒	0.82	“回忆”“ recall”“ recalling”
2. L19N4773+1🕒	0.82	“ remembered”“ recall”“还原”
3. L23N3392+1💤	0.82	“记住了”“记”“记忆”
4. L19N6175-1🕒	0.81	“ years”“回忆”“ recall”
5. L20N8747-1🕒	0.80	“ remembered”“回忆”“ recalled”
6. L28N3095+1💤	0.80	“ remember”“记忆”“ remembering”
7. L20N5027+1🕒	0.79	“ remembering”“ remembers”“ judgement”
8. The Nostalgic✅ L19N5417+1	0.79	“ recalling”“回顾”“回溯”
9. L22N8168-1💥	0.79	“ memory”“记得”“ recall”
10. L22N7210-1💤	0.78	“怀念”“ erinnert”“记”

Shadow specimen, apart from the ten: L20N6110-1💤, 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 20, neuron 6110, 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 0.66) 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
L20N6110+1 t0-v0.1	0.864	0.66	0.977	1.31	Top boosted tokens ↑
L20N6110-1💤 shadow specimen t0-v0.1	0.601	0.73	0.723	1.27	“prem”“ Prem”“ premature”“ ‘”“提前”“ prematurely”“osso”“ terminated”

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.