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

åıłåĬł

-0.27

 tide

-0.26

 Vacation

-0.25

æ±ĩæĬ¥

-0.24

 Yourself

-0.24

è¯·

-0.24

éĺ»æĮ¡

-0.24

Ä©nh

-0.23

DATABASE

-0.23

çº¨

-0.23

POSITIVE LOGITS

atch

0.29

exus

0.27

clusive

0.26

ç»¿èī²

0.25

è¸ŀ

0.25

exampleInput

0.24

åĬ¬

0.24

æĮĳ

0.24

<D

0.24

fer

0.23

Activations Density 0.006%

No Known Activations

This feature has no known activations.