Layer 29 · Neuron 3439 · suppressed

L29N3439-1

Word quirks:

“ –”“ —”“ ——”“ ->”“-ra”“ --”“ -”“<U+00A0>”

💤 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 Qwen3.5, the latest large language model developed by Tong-LLM (T-LLM). My core identity is to be a versatile AI assistant designed to help users across a wide range of tasks — from creative writing and complex reasoning to coding, data analysis, and even multi-step planning.

My Mission

My primary goal is to empower users with intelligent, efficient, and ethical assistance. This translates into three key commitments:

Solve Real Problems: Whether you need to debug a Python script, analyze a research paper, or draft a business plan, I

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. L14N4793+1🕒	0.96	“ –”“ -”“ ——”
2. L17N1991-1💤	0.96	“ --”“ —”“ –”
3. L23N4995-1⛔	0.95	“ –”“ —”“ ——”
4. L21N2004+1🕒	0.94	“ –”“ -”“ —”
5. L14N551+1💤	0.94	“ ——”“ --”“ –”
6. L31N1598+1💥	0.94	“ –”“ --”“ —”
7. L10N2074-1🕒	0.94	“ ——”“ —”“ --”
8. L17N3167-1💤	0.94	“ —”“ ——”“ -”
9. L16N71+1💤	0.94	“ –”“ —”“ ——”
10. L11N3093-1🕒	0.94	“ –”“ —”“ --”

Shadow specimen, apart from the ten: L29N3439+1🕒, 0.46.

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 3439, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.31, top-1 agreement 0.79) 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
L29N3439+1🕒 shadow specimen t0-v0.1	1.169	0.36	1.215	1.18	“-”“¬”“”“-"”“-</”“-.”“ -”“-'”
L29N3439-1 t0-v0.1	0.315	0.79	0.352	1.27	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.