Layer 19 · Neuron 9153 · suppressed

L19N9153-1

Word quirks:

“ hypothetical”“ fictional”“ fict”“ imagined”“ proposed”“ fiction”“ pretend”“ phantom”

🕒 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 Qiancheng, a large language model developed by Fenghua AI (a hypothetical or illustrative scenario; in reality, the next iteration of Qianwen series is Qianchen-1.5). My mission is to serve as a bridge between human creativity and technological possibility, enabling users to achieve their goals through AI. Specifically:

Human-Centric Innovation:

Generate high-quality content (stories, solutions, ideas) for users.
Support real-world applications like research, education, and problem-solving.

Ethical & Responsible AI:

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. L6N8691-1🕒	0.93	“ fictional”“ imaginary”“ fict”
2. L14N2853-1💤	0.89	“ simulated”“ hypothetical”“ fictional”
3. L11N1602-1🕒	0.89	“ fictional”“ hypothetical”“ imagined”
4. L15N739-1🕒	0.88	“ assumed”“ hypothetical”“ imagined”
5. L12N5977+1💤	0.88	“ fictional”“ imaginary”“ simulated”
6. L14N6403-1🕒	0.87	“ fict”“ fictional”“ hypothetical”
7. L12N7994+1🕒	0.87	“ hypothetical”“ imagined”“ thought”
8. L10N9041-1🕒	0.87	“ fake”“ pretend”“ pretending”
9. L9N1143-1🕒	0.86	“ imaginary”“ imagined”“ hypothetical”
10. L13N8875+1🕒	0.85	“ simulated”“ hypothetical”“ imaginary”

Shadow specimen, apart from the ten: L19N9153+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 19, neuron 9153, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.69, top-1 agreement 0.74) 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
L19N9153+1🕒 shadow specimen t0-v0.1	0.730	0.69	0.840	1.24	“ predominant”“ prefixes”“ predominantly”“ efficiente”“ streams”“ shorter”“ primary”“ these”
L19N9153-1 t0-v0.1	0.695	0.74	0.772	1.15	Top boosted tokens ↑

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.