INDEX

Explanations

Code

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĢĢçĸĳ

-0.26

null

-0.26

æĭĴ

-0.25

çİĳ

-0.25

 withhold

-0.25

-null

-0.25

æĺĤ

-0.24

apl

-0.24

éĩįå¤į

-0.24

pom

-0.24

POSITIVE LOGITS

Translations

0.27

çĥĤ

0.27

enko

0.26

/licenses

0.25

 COOKIE

0.25

 Matcher

0.24

INCT

0.24

rika

0.24

datal

0.24

 imageSize

0.24

Activations Density 0.137%

Code

No Comments

No Known Activations