INDEX

Explanations

Abbreviations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

 Liberty

-0.29

åĢĺ

-0.28

ãĤĦãģĻ

-0.27

æĬĸ

-0.27

 liberty

-0.26

å±Ī

-0.26

ictory

-0.26

Ð²Ñĥ

-0.24

actory

-0.24

ulo

-0.24

POSITIVE LOGITS

çŃ¹èµĦ

0.30

uder

0.28

appen

0.27

 franchises

0.26

oodle

0.25

antan

0.25

 Hanna

0.25

åĴ¥

0.25

 pong

0.25

 ì´Īê¸°

0.24

Activations Density 0.002%

Abbreviations

No Comments

No Known Activations