INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åİĭåĬĽ

-0.31

aroo

-0.28

<Real

-0.27

å°±å·²ç»ı

-0.27

å±ŀ

-0.27

çļĦåİĭåĬĽ

-0.27

æ¯Ķä¾ĭ

-0.26

å±ŀäºİ

-0.26

çļĦåŁİå¸Ĥ

-0.26

)(__

-0.26

POSITIVE LOGITS

 mathematics

0.29

 calculus

0.27

format

0.27

 question

0.27

0.26

 questions

0.26

 math

0.25

å°įæĸ¹

0.25

 Question

0.25

 object

0.25

Activations Density 0.080%

No Known Activations

This feature has no known activations.