INDEX

Explanations

advertising

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

 transition

-0.28

transition

-0.28

ç½®

-0.28

ÐµÑĩ

-0.27

-US

-0.27

åĹª

-0.27

lient

-0.26

ç½®äºİ

-0.26

/embed

-0.25

ç¾İåĽ½

-0.25

POSITIVE LOGITS

mop

0.29

 ì»´íĵ¨íĦ°

0.27

 Exact

0.26

é¡ºä¾¿

0.25

éĩĩæļĸ

0.25

 incident

0.25

stm

0.24

exact

0.24

 requestData

0.24

åĽłåŃĲ

0.24

Activations Density 0.005%

advertising

No Comments

No Known Activations