INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æŃ£éĿ¢

-0.30

è·Ŀç¦»

-0.28

 realities

-0.27

 distance

-0.27

çļĦéģĵè·¯

-0.26

_DISTANCE

-0.26

(distance

-0.25

è½²

-0.25

 flash

-0.25

æĭĲ

-0.25

POSITIVE LOGITS

onym

0.30

iali

0.28

 anonymously

0.28

 ActionListener

0.26

_Stop

0.25

ename

0.25

SpaceItem

0.25

 CÃ¢m

0.24

 addTarget

0.24

cassert

0.24

Activations Density 32.313%

No Known Activations

This feature has no known activations.