INDEX

Explanations

INS

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

Hierarchy

-0.25

 deemed

-0.25

 Clifford

-0.23

/MPL

-0.22

HOOK

-0.22

çĽ¸å¯¹äºİ

-0.22

TO

-0.22

toc

-0.22

 brisk

-0.22

åıªè¦ģ

-0.21

POSITIVE LOGITS

å®¤å¤ĸ

0.29

éľīç´ł

0.26

åıĪå¥½

0.25

odyn

0.24

 numÃ©rique

0.23

 afterward

0.23

 autop

0.23

avax

0.23

GetObject

0.23

 Comple

0.23

Activations Density 0.014%

INS

No Comments

No Known Activations