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

ä¸įä¸ĭ

-0.32

 cate

-0.27

iences

-0.26

Dew

-0.26

 beforehand

-0.26

adel

-0.26

è·Łä»ĸ

-0.25

è¿ĻåĿĹ

-0.25

å¯¹ä»ĸ

-0.25

å¤§å¤ļ

-0.25

POSITIVE LOGITS

ä¼´éļı

0.27

 coils

0.27

coil

0.27

PLUS

0.26

å¹³éĿ¢

0.26

AREST

0.25

æĻģ

0.25

èĮ¬

0.25

urus

0.24

ctxt

0.24

Activations Density 0.006%

No Known Activations

This feature has no known activations.