INDEX

Explanations

center

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

bai

-0.28

aq

-0.27

wend

-0.26

æľĢå¤ļçļĦ

-0.25

å®Ī

-0.25

å¡«åĨĻ

-0.25

åīįèĢħ

-0.25

sic

-0.25

iping

-0.24

æİĮ

-0.24

POSITIVE LOGITS

osphate

0.30

pyl

0.28

eci

0.26

ç½¹

0.26

_EXTENSIONS

0.25

æĶ¯çº¿

0.25

 IntelliJ

0.24

_bt

0.24

çĩł

0.24

èĢ³æľº

0.23

Activations Density 0.001%

center

No Comments

No Known Activations