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

oxid

-0.32

uppen

-0.26

æİ¥åĪ°

-0.24

 ÑĥÑĩÐ°ÑģÑĤÐ½Ð¸Ðº

-0.24

artic

-0.24

 pisc

-0.23

ORIZATION

-0.23

Except

-0.23

 pity

-0.23

 XBOOLE

-0.23

POSITIVE LOGITS

åıį

0.27

tet

0.27

tet

0.25

åĴ¯

0.25

 courses

0.25

XR

0.24

idel

0.24

tone

0.24

awei

0.24

eh

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.