Layer 28 · Neuron 7774 · suppressed

L28N7774-1

Word quirks:

“ med”“zan”“ Burgess”“二次”“走廊”“ Med”“chio”“ Ally”

💤 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 in the Qwen series developed by Tongyi Lab. My core mission is to empyacally assist users across a wide range of tasks by leveraging my advanced capabilities in linguistic understanding, logical reasoning, code generation, and cross-lingual communication.

Key Objectives:

Precision & Accuracy:

Deliver high-quality responses in 100+ languages with deep comprehension of context, nuance, and cultural subtillities.

Task Coverage:

**All-rou

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. L29N7363-1🕒	0.66	“ med”“鉴”“下山”
2. L28N7168-1💤	0.65	“ Med”“emet”“chain”
3. L27N6234+1🕒	0.65	“ Med”“-med”“ Mede”
4. L25N8790+1💤	0.63	“achten”“ Julian”“介质”
5. L25N6524+1💤	0.62	“ med”“ Med”“แท”
6. L25N9171+1🕒	0.61	“ med”“武”“Med”
7. L26N4367+1🕒	0.60	“ Med”“ Mad”“Med”
8. L26N3601+1🕒	0.60	“中新”“.med”“ med”
9. L26N5206-1🕒	0.60	“ med”“ Med”“Smooth”
10. L27N3112+1💤	0.60	“upy”“upt”“ med”

Shadow specimen, apart from the ten: L28N7774+1🕒, 0.44.

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 28, neuron 7774, 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 0.82) 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
L28N7774+1🕒 shadow specimen t0-v0.1	0.414	0.76	0.525	1.57	“gel”“íg”“ Strat”“奶”“魂”“lag”“摩”“otos”
L28N7774-1 t0-v0.1	0.312	0.82	0.276	1.31	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.