INDEX

Explanations

advance

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

ields

-0.28

 doubles

-0.27

æĪĺçģ«

-0.24

å®ļ

-0.24

zel

-0.24

Ø¸Ùħ

-0.24

åĿļæĮģ

-0.24

versible

-0.23

oubles

-0.23

ronics

-0.23

POSITIVE LOGITS

èģªæĺİ

0.27

Insn

0.27

èŀ³

0.27

igne

0.27

perse

0.27

/down

0.25

kir

0.25

lek

0.25

äººæīį

0.24

iteration

0.24

Activations Density 0.002%

advance

No Comments

No Known Activations