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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĢĢæ¬¾

-0.27

olina

-0.27

ponge

-0.27

==(

-0.24

edImage

-0.24

Traits

-0.24

arf

-0.24

arie

-0.23

 younger

-0.23

å¸¸

-0.23

POSITIVE LOGITS

æĸ°éĻĪä»£è°¢

0.30

 countered

0.30

 Others

0.26

puts

0.25

nels

0.25

iosis

0.24

 puts

0.23

åŁļ

0.23

æĲŃæ¡£

0.23

 cycle

0.23

Activations Density 0.012%

No Known Activations

This feature has no known activations.