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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rone

-0.27

mij

-0.27

æ²¡è§ģè¿ĩ

-0.26

bane

-0.25

é«Ń

-0.25

éĢĢ

-0.24

æĮĤåľ¨

-0.24

å¾ĹäºĨ

-0.23

ħĮ

-0.23

åĿĮ

-0.23

POSITIVE LOGITS

rev

0.31

æĳĨ

0.26

/slick

0.26

 rails

0.26

å°±å¥½

0.25

osci

0.25

Hub

0.24

rev

0.24

aton

0.24

SAS

0.24

Activations Density 0.003%

No Known Activations

This feature has no known activations.