INDEX

Explanations

out

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

itage

-0.32

Ø³ØªØ±

-0.28

ä¸Ģè·¯

-0.26

vier

-0.26

bj

-0.26

ãģĦãģı

-0.26

utr

-0.25

åİ»

-0.25

mission

-0.25

esis

-0.24

POSITIVE LOGITS

YRO

0.26

åīįç½®

0.25

mts

0.24

.getFile

0.24

asn

0.24

 Lionel

0.24

 muzzle

0.23

amos

0.23

çİĩåħĪ

0.23

âĬĬ

0.23

Activations Density 0.002%

out

No Comments

No Known Activations