INDEX

Explanations

Code or unusual characters

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

)["

-0.26

emes

-0.25

uri

-0.24

æ·ĳ

-0.24

rien

-0.23

.EN

-0.23

 Ð¦ÐµÐ½Ð°

-0.23

URI

-0.23

oy

-0.23

å®Į

-0.23

POSITIVE LOGITS

 Assassin

0.26

finder

0.26

æī¹ç¤º

0.25

bulk

0.25

 common

0.25

åĨħç§ĳ

0.25

Ãłnh

0.25

 subconscious

0.24

getRow

0.24

he

0.24

Activations Density 0.001%

Code or unusual characters

No Comments

No Known Activations