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

æĸĩåĮĸèīºæľ¯

-0.27

éĻįä¸´

-0.25

DU

-0.24

atri

-0.24

ialect

-0.24

atform

-0.23

'")↵

-0.22

mutation

-0.22

 sple

-0.22

éĴŀ

-0.22

POSITIVE LOGITS

olley

0.28

uur

0.28

yer

0.26

uko

0.26

 chan

0.25

çŁ¶

0.25

haft

0.25

çļĦè®¤è¯Ĩ

0.25

sap

0.24

uru

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.