INDEX

Explanations

of

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

uben

-0.30

çª¦

-0.28

çļĦéĢļçŁ¥

-0.26

arrant

-0.25

 Volunteers

-0.25

allel

-0.25

roscope

-0.25

otify

-0.25

ç¼©

-0.24

éĢļçŁ¥

-0.24

POSITIVE LOGITS

Nom

0.28

isas

0.27

ipel

0.27

æł¼

0.26

 decades

0.26

ledged

0.26

lrt

0.26

éĻĲéĩı

0.26

NOM

0.25

èĤ¥

0.25

Activations Density 0.001%

of

No Comments

No Known Activations