INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ude

-0.25

_dropout

-0.25

 cá»Ń

-0.25

 Lazy

-0.24

 sond

-0.24

>(()

-0.24

adget

-0.23

à¸ķà¸£à¸²

-0.23

endet

-0.23

Ð´Ð¸Ð½

-0.23

POSITIVE LOGITS

folk

0.26

æĶ¾ç½®

0.26

lay

0.26

back

0.25

kn

0.25

åľ¨æĹ¥æľ¬

0.25

 proper

0.25

 back

0.25

layout

0.25

expanded

0.25

Activations Density 0.906%

No Known Activations

This feature has no known activations.