INDEX

Explanations

be

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

TR

-0.30

bean

-0.26

pry

-0.26

osci

-0.25

Toggle

-0.25

iores

-0.24

_^

-0.24

phys

-0.24

->$

-0.23

åĴĮæľįåĬ¡

-0.23

POSITIVE LOGITS

fraction

0.27

.newInstance

0.25

sup

0.25

å½Ģ

0.25

ç¼ļ

0.24

Fraction

0.24

åıĪè¢«

0.24

 constitu

0.24

ä¸ĬçļĦ

0.24

_fraction

0.23

Activations Density 0.010%

be

No Comments

No Known Activations