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

_dash

-0.27

ooks

-0.26

odash

-0.26

 condu

-0.26

agher

-0.25

 lieutenant

-0.25

ights

-0.24

ç¼ºåı£

-0.24

lobe

-0.24

æıĲåįĩ

-0.24

POSITIVE LOGITS

Levels

0.28

 Hanging

0.26

Jah

0.25

 Location

0.25

ç¢İ

0.24

dera

0.24

 Saving

0.24

ä¹ĭä¸ĭ

0.24

 :↵↵↵↵

0.24

 Krishna

0.23

Activations Density 0.082%

No Known Activations

This feature has no known activations.