INDEX

Explanations

course

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

 escorted

-0.25

çĤĢ

-0.25

 tonight

-0.25

_TYP

-0.24

æĺİæ¸ħ

-0.24

 Dirt

-0.24

 certify

-0.23

è¯ļå®ŀ

-0.23

åģ¥åº·æĪĲéķ¿

-0.23

edly

-0.23

POSITIVE LOGITS

fly

0.30

chemist

0.29

RI

0.28

 Wolfe

0.27

stands

0.26

onium

0.26

ide

0.25

fly

0.25

stants

0.25

ylie

0.24

Activations Density 0.076%

course

No Comments

No Known Activations