INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æīĢä»¥è¯´

-0.27

-lat

-0.26

Ð¼Ð¾ÑĢ

-0.25

 Herc

-0.25

ä¸Ģç¢Ĺ

-0.25

ä¸ĢæŃ¥

-0.25

ä¸ĢçĤ¹

-0.24

ä¸Ģç¨®

-0.24

antic

-0.24

LatLng

-0.24

POSITIVE LOGITS

\f

0.31

ement

0.29

aro

0.28

hea

0.28

ing

0.26

å¯¹èĩªå·±çļĦ

0.26

raf

0.25

RA

0.24

edly

0.24

epad

0.24

Activations Density 11.793%

No Known Activations

This feature has no known activations.