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

Not in Any Lists

No Comments

Negative Logits

im

-0.29

ort

-0.28

 modeling

-0.27

.cg

-0.26

=index

-0.25

ime

-0.25

,,

-0.25

.basic

-0.25

tures

-0.25

 outside

-0.24

POSITIVE LOGITS

soever

0.27

æºī

0.27

Decorator

0.26

issing

0.25

Ð¸ÑĦÐ¸ÐºÐ°

0.24

æµĵ

0.24

 downt

0.24

åĬŁè¯¾

0.23

idable

0.23

åıĺå¾ĹæĽ´

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.