INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

Getter

-0.26

etched

-0.25

&m

-0.23

odb

-0.23

ä½ľèĢħ

-0.23

éļĺ

-0.23

 stabilization

-0.23

_picker

-0.22

breaker

-0.22

ITS

-0.22

POSITIVE LOGITS

prene

0.24

zd

0.24

åµĮ

0.24

moz

0.23

aurant

0.23

ç»ĵåĲĪ

0.23

ï¬Ĥ

0.23

 createState

0.23

Kas

0.22

 trans

0.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.