Layer 28 · Neuron 1414 · boosted

L28N1414+1

Word quirks:

“chet”“佛”“ulen”“opat”“istol”“olon”“ettino”“jö”

💤 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 Tongji Lab (Alibaba Cloud). My mission is to empower users with intelligent, reliable, and context-aware assistance across a wide range of tasks—whether that's solving complex problems, creating content, coding, or simply having a conversation.

Key aspects of my mission:

Precision & Context Awareness:

I excel at understanding long contexts (up to 256K tokens) and multi-step reasoning, ensuring accurate answers even in intricate scenarios like legal analysis, scientific research, or multi-language dialogue.

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. L30N7622+1💤	0.73	“venz”“rox”“ulk”
2. L31N8170-1💥	0.72	“otan”“木齐”“条”
3. L29N140+1💤	0.71	“alos”“udin”“ouz”
4. L28N2707-1💤	0.70	“eter”“ino”“ritz”
5. L31N7236+1💥	0.70	“idel”“اظ”“onio”
6. L29N5811+1💤	0.70	“oxy”“oble”“այ”
7. L29N5674+1💤	0.70	“olio”“olut”“jew”
8. L31N8574-1💥	0.69	“aura”“�”“ phu”
9. L29N8769+1🕒	0.69	“olni”“ovich”“翻”
10. L31N9041+1💥	0.69	“操”“ffb”“hati”

Shadow specimen, apart from the ten: L28N1414-1🕒, 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 28, neuron 1414, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.20, top-1 agreement 0.84) 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
L28N1414+1 t0-v0.1	0.196	0.84	0.231	1.18	Top boosted tokens ↑
L28N1414-1🕒 shadow specimen t0-v0.1	1.503	0.46	1.519	0.74	“近”“ near”“ Near”“Near”“的近”“了近”“near”“在近”

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.