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

azon

-0.30

-equiv

-0.27

åĪĨæĶ¯

-0.25

.getBytes

-0.25

Browse

-0.25

 ê²°êµŃ

-0.24

 –↵↵

-0.24

 honoring

-0.24

declaring

-0.24

 bred

-0.23

POSITIVE LOGITS

ot

0.27

mel

0.27

archives

0.25

è¯¥æ¡Ī

0.25

wen

0.25

real

0.24

#.

0.24

ç¨ĭ

0.24

owitz

0.23

rc

0.23

Activations Density 0.008%

No Known Activations

This feature has no known activations.