INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¿Ļä»¶

-0.34

 delayed

-0.28

æĦıä¹ī

-0.27

çļĩåĨł

-0.26

 trivial

-0.25

 burns

-0.25

gra

-0.25

Ø³Ùģ

-0.24

 tard

-0.24

ÑĩÑĮ

-0.24

POSITIVE LOGITS

 Chore

0.29

ius

0.29

 acceptance

0.25

uest

0.25

çĮĽåľ°

0.25

egin

0.24

ore

0.24

ries

0.24

rames

0.24

 ÐºÐ°Ñĩ

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.