INDEX

Explanations

pending

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

éĶģ

-0.29

éĢł

-0.28

ICA

-0.26

beh

-0.26

äººåı£

-0.26

è®³

-0.25

 Chat

-0.25

rev

-0.25

ICO

-0.25

ute

-0.25

POSITIVE LOGITS

åıĪå¥½

0.32

çĶŁæ´»åŀĥåľ¾

0.27

ssel

0.27

æ³Ĺ

0.27

 USPS

0.25

 feas

0.24

 morally

0.24

åįłåľ°

0.24

iÃŁ

0.24

 Hubb

0.24

Activations Density 0.002%

pending

No Comments

No Known Activations