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

 igen

-0.29

 floors

-0.28

æ¶²

-0.25

liqu

-0.24

é¥¼

-0.24

leet

-0.24

band

-0.24

å®ŀéĻħæĥħåĨµ

-0.23

æ°¸

-0.23

à¹ģà¸ªà¸Ķà¸ĩ

-0.23

POSITIVE LOGITS

APO

0.28

prech

0.28

 tits

0.27

åľ¨æĪĳçļĦ

0.26

LSD

0.26

urons

0.26

>null

0.24

 OPTIONS

0.24

urch

0.24

unts

0.24

Activations Density 0.004%

No Known Activations

This feature has no known activations.