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

æŀļ

-0.29

éĩı

-0.27

 underlying

-0.25

mut

-0.25

Privacy

-0.25

la

-0.24

cm

-0.23

ä¸įé¡¾

-0.23

 privacy

-0.23

æ¦Ĥå¿µ

-0.23

POSITIVE LOGITS

ervers

0.25

Ð´ÑĢÐ°

0.25

"[

0.25

libraries

0.24

Ã»t

0.23

cente

0.23

istica

0.23

[${

0.23

éĹªåħī

0.23

UPI

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.