INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

df

-0.29

æłı

-0.28

rise

-0.26

çĭĲ

-0.24

è¸Į

-0.23

áºŃy

-0.23

Peer

-0.23

ç½Ķ

-0.23

 Link

-0.23

æŀ¸æĿŀ

-0.23

POSITIVE LOGITS

moduleId

0.27

ä½Ĺ

0.26

evt

0.26

-packages

0.26

 moduleId

0.25

è¿ĽæŃ¥

0.25

èģĮä¸ļæĬĢæľ¯

0.25

ynos

0.24

ort

0.24

-y

0.23

Activations Density 0.153%

No Known Activations

This feature has no known activations.