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

out

-0.33

å¥½äºĭ

-0.29

 null

-0.29

 nicely

-0.28

 directly

-0.28

ä¸įä¿¡

-0.27

 cautiously

-0.27

 inside

-0.27

 later

-0.26

null

-0.26

POSITIVE LOGITS

 Depths

0.29

ilters

0.27

æŀļ

0.26

 actionTypes

0.25

 Passport

0.25

å¸ĥå°Ķ

0.25

GGLE

0.24

 Strap

0.24

áº·ng

0.24

 Pixels

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.