INDEX

Explanations

auc

np_max-act · gemini-2.0-flash

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

è²«

-0.29

 Panels

-0.27

adb

-0.27

oron

-0.27

ignon

-0.25

idot

-0.25

 prob

-0.25

↵                        ↵

-0.24

rove

-0.24

acked

-0.24

POSITIVE LOGITS

éĵĥ

0.30

 taille

0.27

æ¡ħ

0.26

IX

0.26

mile

0.25

ult

0.25

.Endpoint

0.25

éĿ¢çĽ®

0.24

]+$

0.24

ware

0.24

Activations Density 0.002%

auc

No Comments

No Known Activations