INDEX

Explanations

nan

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

 ONLINE

-0.27

amax

-0.26

 Samp

-0.26

çĪĨ

-0.25

NEO

-0.24

-online

-0.24

 epile

-0.23

å°¾å·´

-0.23

 Wheel

-0.23

,password

-0.23

POSITIVE LOGITS

nan

0.60

çº³ç±³

0.57

nan

0.51

 nano

0.47

Nan

0.44

nano

0.42

Nano

0.41

nm

0.41

nm

0.40

.nan

0.39

Activations Density 0.049%

nan

No Comments

No Known Activations