INDEX

Explanations

is

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

atoire

-0.27

 Anders

-0.27

ughty

-0.26

åľ¨è·¯ä¸Ĭ

-0.25

 reacted

-0.25

ARENT

-0.25

ÃŃcio

-0.24

fty

-0.24

è¾ľ

-0.24

 reactions

-0.23

POSITIVE LOGITS

divider

0.27

_losses

0.27

okens

0.26

æĿ¾å¼Ľ

0.25

/class

0.25

edium

0.25

utherland

0.25

cÃŃ

0.25

otics

0.24

.setSelection

0.24

Activations Density 0.444%

is

No Comments

No Known Activations