INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çģ°

-0.32

_FAST

-0.30

awaii

-0.27

 basal

-0.26

éļ°

-0.26

presso

-0.25

zas

-0.25

åŃ¤

-0.25

å¼¥

-0.25

Ø§ÙĪÙĬ

-0.25

POSITIVE LOGITS

ì²´

0.27

storm

0.27

 entity

0.25

 tape

0.25

éķ¿çŁŃ

0.25

å·¥ä½ľç«Ļ

0.24

izing

0.24

è¿ĳ

0.24

how

0.23

andExpect

0.23

Activations Density 0.008%

No Known Activations

This feature has no known activations.