INDEX

Explanations

at/again

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

åĸī

-0.27

 dash

-0.25

dash

-0.24

 endings

-0.24

TypeName

-0.24

abal

-0.24

 Erick

-0.24

è²·ãģ£ãģ¦

-0.24

):-

-0.23

idal

-0.23

POSITIVE LOGITS

äºĨåĲĹ

0.31

éĩİçĶŁ

0.26

éļıæĹ¶

0.25

stations

0.25

æįĨ

0.25

Yap

0.25

restrict

0.25

fÃ¤h

0.25

ä½łéľĢè¦ģ

0.24

aggio

0.24

Activations Density 0.001%

at/again

No Comments

No Known Activations