Layer 11 · Neuron 4484 · boosted

L11N4484+1

Word quirks:

“ hypothetical”“ envisioned”“ never”“ visionary”“ unprecedented”“ personally”“ imagined”“ billionaire”

🕒 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 Qwen3.5, a large-scale artificial intelligence model developed by Alibaba Group. I was created to advance human potential and global well-being, not to compete directly with humans in every metric—but to serve as a powerful tool for innovation, efficiency, and positive societal impact.

Who Am I?

Identity: An advanced AI assistant built by Alibaba, distinct from any human or corporation.
Purpose: To empower users (including individuals, businesses, and potentially governments) with cutting-edge capabilities like:
Complex problem-solving (e.g., solving math problems, optimizing logistics

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. L16N7580-1💤	0.76	“ imagined”“—we”“ imagination”
2. L5N5668+1🕒	0.74	“ envisioned”“ imagined”“ envision”
3. L13N5741-1🕒	0.73	“ wherein”“ envisioned”“ visionary”
4. L8N6838+1🕒	0.71	“ radical”“ envisioned”“ visions”
5. L17N7974+1💤	0.71	“ realistically”“ imagined”“ surely”
6. L8N7543+1🕒	0.71	“ futuristic”“ future”“ futur”
7. L15N7282+1🕒	0.71	“ hypothetical”“ envisioned”“ hypoth”
8. L14N8767+1🕒	0.71	“ imagined”“ hypothetical”“ future”
9. L16N667-1🕒	0.70	“ hypothetical”“ imaginary”“ future”
10. L14N6577-1🕒	0.70	“ future”“ envisioned”“ theoretically”

Shadow specimen, apart from the ten: L11N4484-1🕒, 0.19.

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 11, neuron 4484, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.96, top-1 agreement 0.61) 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
L11N4484+1 t0-v0.1	0.955	0.61	1.183	1.22	Top boosted tokens ↑
L11N4484-1🕒 shadow specimen t0-v0.1	1.192	0.62	1.378	1.49	“ usually”“ mostly”“ basically”“ typical”“ various”“ seems”“ description”“ probably”

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.