INDEX

Explanations

technical/scientific content

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

elling

-0.29

 jointly

-0.28

çķĪ

-0.26

åĽĽçº§

-0.26

ê¸ī

-0.25

odon

-0.25

iage

-0.25

ny

-0.25

å¤§åıĳ

-0.25

lip

-0.25

POSITIVE LOGITS

åŃ¤ç«ĭ

0.29

apore

0.26

à¹Ģà¸¨

0.26

æ·ĩ

0.26

æĮĤåľ¨

0.26

NECT

0.24

 salute

0.24

 Prop

0.24

prop

0.24

.Prop

0.24

Activations Density 0.002%

technical/scientific content

No Comments

No Known Activations