INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

èħĶ

-0.30

venge

-0.28

åĬŁå¤«

-0.27

appings

-0.27

agus

-0.25

é£

-0.25

çļĦèĥ½éĩı

-0.24

æĶ¾åĩº

-0.24

 Himself

-0.23

 '''č↵

-0.23

POSITIVE LOGITS

 trust

0.33

åıĳå±ķåİĨç¨ĭ

0.28

net

0.27

_net

0.26

trust

0.25

ä¿¡ä»»

0.25

nhi

0.25

rat

0.24

æķĳ

0.24

ain

0.24

Activations Density 0.039%

No Known Activations

This feature has no known activations.