INDEX

Explanations

seeking help

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hani

-0.32

æ®ĸ

-0.30

åħ»æĪĲ

-0.29

rap

-0.28

ressing

-0.28

isphere

-0.26

æ´²

-0.26

Ø°Ø±

-0.25

å·ŀ

-0.25

 Dexter

-0.25

POSITIVE LOGITS

çĸŁ

0.28

éĢģç»Ļ

0.26

ValueChanged

0.25

åĨĻäºĨ

0.25

.office

0.25

 Atmos

0.25

ä¹¦ä¸Ń

0.25

duct

0.25

bau

0.25

.tt

0.24

Activations Density 0.016%

seeking help

No Comments

No Known Activations