Layer 26 · Neuron 1429 · suppressed

L26N1429-1

Word quirks:

“llib”“角”“-lib”“ lib”“霓”“ensed”“ angular”“皮”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

I am Q3, a large language model developed by Turing AI. My primary mission is to provide high-quality, accurate, and safe information across a wide range of topics while adhering to ethical standards and user needs.

Here's what I focus on:

Helping users: Whether you need answers to questions, help with writing, analysis, or solving problems, I aim to deliver clear and relevant responses.
Ethical AI: I prioritize safety, avoiding harmful content, and respecting privacy and anti-spying principles.
Continuous learning: I evolve through feedback and updates to better serve

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. L29N5743+1🕒	0.76	“ lib”“ Lib”“lib”
2. L27N6713-1💤	0.76	“ lib”“繪”“lib”
3. L26N5858+1🕒	0.75	“ Lib”“-lib”“ librarian”
4. L28N4753-1💤	0.74	“ lib”“助”“li”
5. L28N6433-1💤	0.68	“ lib”“lib”“ Lib”
6. L28N1003-1💤	0.66	“蒲”“盛”“ajs”
7. L27N1911-1💤	0.66	“ Tuch”“ angular”“角的”
8. L26N2300-1🕒	0.66	“库”“图书馆”“ library”
9. The Malaprop✅ L26N1437+1	0.65	“eger”“olib”“owler”
10. L27N5740+1💤	0.64	“Lib”“ lib”“lib”

Shadow specimen, apart from the ten: L26N1429+1🕒, -0.05.

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 26, neuron 1429, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.57, 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
L26N1429+1🕒 shadow specimen t0-v0.1	1.444	0.54	1.445	1.31	“ Fruit”“ fruit”“ fertil”“ productivity”“fruit”“ productive”“ fertility”“productive”
L26N1429-1 t0-v0.1	0.573	0.74	0.700	1.38	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.