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

supported

-0.27

åı¯è§ĨåĮĸ

-0.27

çĦķ

-0.25

åľ»

-0.25

äºĨèµ·æĿ¥

-0.24

à²Ł

-0.24

èµ·æĿ¥äºĨ

-0.24

#get

-0.23

zug

-0.23

 Sebast

-0.23

POSITIVE LOGITS

 inclusion

0.29

 deduction

0.27

<<-

0.26

 contro

0.26

swe

0.25

ãĥ¯ãĥ¼

0.24

èıģ

0.24

èĳ±

0.24

nga

0.24

 pace

0.24

Activations Density 0.016%

No Known Activations

This feature has no known activations.