INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Entr

-0.27

rÃ£o

-0.26

ConverterFactory

-0.26

¡°

-0.25

æĻ¨æĬ¥

-0.24

rown

-0.24

 ENTRY

-0.24

entr

-0.24

poser

-0.24

ACITY

-0.24

POSITIVE LOGITS

vit

0.30

 just

0.26

ici

0.26

åĲ¬åĬĽ

0.26

ii

0.25

Ã©ri

0.25

å°±åľ¨

0.25

 dose

0.25

CUS

0.25

im

0.24

Activations Density 10.722%

No Known Activations

This feature has no known activations.