INDEX

Explanations

Q&A and medical text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BA

-0.27

 match

-0.25

åĳ¨ä¸Ģ

-0.25

æĥħ

-0.25

 remind

-0.24

 closet

-0.24

åĬ©

-0.24

æĴĩ

-0.24

BA

-0.24

 sling

-0.23

POSITIVE LOGITS

etch

0.30

ETCH

0.29

verbs

0.26

ymi

0.26

hores

0.25

achu

0.25

czÄĻ

0.24

/DTD

0.23

æīĵç£¨

0.23

addy

0.23

Activations Density 0.000%

Q&A and medical text

No Comments

No Known Activations