INDEX

Explanations

oping

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

olis

-0.28

 Cornwall

-0.27

asters

-0.26

.sav

-0.25

rotation

-0.25

RefCount

-0.24

ç§©

-0.24

 Singular

-0.24

_ATTRIB

-0.24

ä¸»èĲ¥ä¸ļåĬ¡

-0.24

POSITIVE LOGITS

rette

0.26

uf

0.26

Jr

0.25

UIB

0.25

uth

0.25

ftar

0.25

çļ®

0.24

ana

0.24

å¹¼

0.24

è¿Ľåħ¥

0.24

Activations Density 0.830%

oping

No Comments

No Known Activations