INDEX

Explanations

about

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ole

-0.27

DK

-0.25

KL

-0.25

alia

-0.25

ersh

-0.25

CT

-0.24

åıĺå¹»

-0.24

 pours

-0.24

èĥ¶

-0.24

POSITIVE LOGITS

ensem

0.31

 maintaining

0.29

 fool

0.29

idot

0.28

ppv

0.27

arness

0.26

emade

0.26

 apprent

0.25

 NSLayoutConstraint

0.25

accur

0.25

Activations Density 0.008%

about

No Comments

No Known Activations