INDEX

Explanations

conversational/everyday writing

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

echo

-0.31

 echoes

-0.30

 echo

-0.27

 Uncomment

-0.26

vue

-0.26

.bootstrap

-0.26

pants

-0.26

 began

-0.26

ome

-0.26

"Now

-0.25

POSITIVE LOGITS

ç¿¦

0.26

agr

0.25

åīįä¸Ģå¤©

0.25

 labs

0.24

.DriverManager

0.24

 demean

0.24

-drive

0.24

istra

0.24

 willingness

0.23

ä¹ħ

0.23

Activations Density 0.003%

conversational/everyday writing

No Comments

No Known Activations