INDEX

Explanations

position

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

æĲģ

-0.29

SOR

-0.26

>::

-0.25

 OTHERWISE

-0.25

iou

-0.25

æİ¥åıĹäºĨ

-0.25

HCI

-0.24

akis

-0.24

krit

-0.24

GOT

-0.24

POSITIVE LOGITS

ÃŃg

0.28

æģª

0.27

 Liberals

0.26

Cheap

0.25

 Chemistry

0.25

ray

0.25

æĭ¼

0.25

uffer

0.24

 cinema

0.24

DidLoad

0.24

Activations Density 0.003%

position

No Comments

No Known Activations