INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

emat

-0.30

ä¸Ģä»£

-0.29

ä¸Ģå¹´ä¸Ģåº¦

-0.27

å¸

-0.27

ä¸Ģè§Ī

-0.27

ä»»æĢ§

-0.26

ims

-0.25

 License

-0.25

License

-0.24

éķľå¤´

-0.23

POSITIVE LOGITS

 achievable

0.27

(Direction

0.25

parable

0.25

 tolua

0.25

ozy

0.25

çķĽ

0.24

yleft

0.24

èĥ½æ»¡è¶³

0.24

zia

0.24

IVEN

0.23

Activations Density 0.090%

No Known Activations

This feature has no known activations.