Layer 25 · Neuron 2874 · boosted

L25N2874+1

Word quirks:

“achel”“布里”“付け”“劈”“团”“zia”“佑”“ прон”

🕒 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 G* (Giga) is a large-scale language model with a focus on providing helpful, accurate, and culturally relevant information. My mission is to *assist users in solving problems, creating content, and learning new things by offering clear explanations, creative solutions, and tailored assistance across a wide range of topics.

Whether you need help with:

Complex analysis (e.g., scientific concepts or data analysis)
Creative tasks (e.g., writing stories, scripts, or code)
Daily assistance (e.g., planning, summarizing, or explaining concepts)
**

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. L24N7230+1💤	0.78	“布里”“伏”“推”
2. L31N2362+1💥	0.77	“褚”“夷”“鞭”
3. L28N774-1💤	0.77	“iker”“睿”“螺杆”
4. L28N4673-1💤	0.76	“agon”“敷”“亚”
5. L30N4012+1🕒	0.76	“彦”“昌”“玮”
6. L30N6462-1💤	0.76	“揣”“压”“鹰”
7. L25N136-1💤	0.76	“hren”“akaran”“adeira”
8. L30N2953+1💤	0.76	“休”“峪”“纪”
9. L30N7173-1💤	0.76	“弥”“柄”“色”
10. L25N7689-1🕒	0.76	“acun”“摇摇”“تاب”

Shadow specimen, apart from the ten: L25N2874-1🕒, 0.02.

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 25, neuron 2874, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.63, 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
L25N2874+1 t0-v0.1	0.632	0.74	0.664	1.45	Top boosted tokens ↑
L25N2874-1🕒 shadow specimen t0-v0.1	1.257	0.59	1.293	0.93	“ read”“ reads”“读”“Read”“-read”“ Read”“read”“ reading”

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.