INDEX

Explanations

item

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

_ELEMENTS

-0.25

utivo

-0.25

ERY

-0.24

icho

-0.24

åħĥä»¶

-0.24

äºĭé¡¹

-0.24

ino

-0.24

compound

-0.23

 Junction

-0.23

 toString

-0.23

POSITIVE LOGITS

åĮĸçļĦ

0.28

ized

0.27

ãģĴãĤĭ

0.25

otropic

0.25

-lines

0.24

fox

0.24

åĥĸ

0.24

acus

0.24

Fed

0.23

êµ°

0.22

Activations Density 0.136%

item

No Comments

No Known Activations