INDEX

Explanations

status/deficiency

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

ä¸ĵ

-0.28

@stop

-0.28

æĭĴ

-0.26

Sz

-0.24

-serif

-0.24

NaN

-0.24

Sz

-0.24

 flatten

-0.24

æ¸ł

-0.23

èĢģäºº

-0.23

POSITIVE LOGITS

èģ¿

0.28

 recru

0.28

lettes

0.26

asure

0.26

Comparable

0.26

 loadData

0.25

æĢħ

0.25

 Radi

0.25

(Key

0.24

 gradu

0.24

Activations Density 0.004%

status/deficiency

No Comments

No Known Activations