INDEX

Explanations

names

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

 kÃª

-0.28

æīĢèĩ´

-0.28

è´¢

-0.26

ç¨ł

-0.26

éħ¥

-0.26

 Individuals

-0.26

endant

-0.25

çľĭä¸Ģçľĭ

-0.25

-treated

-0.25

 merit

-0.25

POSITIVE LOGITS

 transfer

0.27

 unreal

0.26

unpack

0.25

 COMPONENT

0.25

hound

0.25

transfer

0.25

 Chore

0.24

æĩĭ

0.24

 unst

0.24

.transfer

0.23

Activations Density 0.001%

names

No Comments

No Known Activations