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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĩĢ

-0.27

_HOLD

-0.26

æĮģ

-0.26

æĮģæľīäºº

-0.25

holder

-0.24

CFG

-0.24

ĶåĽŀ

-0.24

 compass

-0.23

tlement

-0.23

çĽĺ

-0.23

POSITIVE LOGITS

ä¹ĲåĽŃ

0.33

AMI

0.27

 elasticity

0.26

åĨħé©¬

0.25

lix

0.25

isms

0.25

leh

0.25

éļħ

0.25

amel

0.25

æĺ¯ä»¥

0.25

Activations Density 26.919%

No Known Activations

This feature has no known activations.