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

èĮ¹

-0.27

åĮĪ

-0.27

^K

-0.27

 Regents

-0.26

çªģçł´åı£

-0.24

æľĪåºķ

-0.24

rus

-0.24

éĦ£

-0.24

PYTHON

-0.23

 COPYING

-0.23

POSITIVE LOGITS

çļĦåħ·ä½ĵ

0.28

èļĵ

0.26

.FindAsync

0.25

iosis

0.25

etric

0.25

opia

0.24

 Everest

0.24

olders

0.24

asic

0.24

 getTitle

0.24

Activations Density 0.010%

No Known Activations

This feature has no known activations.