Layer 29 · Neuron 5743 · boosted

L29N5743+1

Word quirks:

“ lib”“ Lib”“lib”“原”“-lib”“(lib”“_lib”“片”

🕒 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, the latest large language model developed by Allibn (原通义千问). My core mission is to serve as a versatile, reliable, and ethical AI assistant that empowers users across diverse scenarios—whether for creative writing, complex reasoning, coding, or long-term memory management.

Key aspects of my mission:

Bridge the gap between human intent and digital execution:

I help users turn abstract ideas into concrete outcomes—crafting stories, debugging code, analyzing data, or planning long-term projects—with clear, actionable results.

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. L30N282+1💥	0.93	“lib”“ lib”“Lib”
2. L26N2642-1🕒	0.93	“ lib”“ Lib”“-lib”
3. L27N5740+1💤	0.92	“Lib”“ lib”“lib”
4. L28N6433-1💤	0.92	“ lib”“lib”“ Lib”
5. L29N4523+1🕒	0.90	“ lib”“lib”“Lib”
6. L28N5037-1🕒	0.90	“lib”“ lib”“Lib”
7. L28N4753-1💤	0.88	“ lib”“助”“li”
8. L26N5858+1🕒	0.87	“ Lib”“-lib”“ librarian”
9. L23N1138+1🕒	0.87	“ library”“-library”“ religion”
10. L27N4236-1💤	0.86	“lib”“ lib”“ lab”

Shadow specimen, apart from the ten: L29N5743-1💤, 0.13.

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 29, neuron 5743, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.32, top-1 agreement 0.81) 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
L29N5743+1 t0-v0.1	0.323	0.81	0.433	1.45	Top boosted tokens ↑
L29N5743-1💤 shadow specimen t0-v0.1	0.295	0.82	0.311	1.53	“rat”“gemeinschaft”“-pe”“ ,-”“抽空”“看得”“eldet”“ peptide”

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.