INDEX

Explanations

question mark

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

å¯¸

-0.33

#__

-0.27

aso

-0.27

 evaluation

-0.26

.Evaluate

-0.26

ç»Ī

-0.26

ç®±

-0.24

à¸Ĭ

-0.24

ssÃ©

-0.24

box

-0.24

POSITIVE LOGITS

 explan

0.27

Apis

0.27

çı°

0.24

apis

0.24

Explanation

0.24

 repost

0.23

 [...]

0.23

Radi

0.23

cyl

0.23

iban

0.22

Activations Density 0.160%

question mark

No Comments

No Known Activations