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

orthand

-0.27

lings

-0.26

Slinky

-0.25

rÃ¡f

-0.25

 graphic

-0.25

illis

-0.24

 tight

-0.24

$$$

-0.24

WindowState

-0.24

duk

-0.24

POSITIVE LOGITS

using

0.28

aget

0.26

cons

0.25

Validation

0.25

 Hearing

0.24

bez

0.24

æĺ¯ä¸įåı¯èĥ½

0.24

oya

0.23

isc

0.23

åĲ¬

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.