INDEX

Explanations

which

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

Ã©rique

-0.30

 compromise

-0.29

 Dimension

-0.26

å¯¹åħ¬åı¸

-0.26

)obj

-0.26

Dimension

-0.26

ÐºÑĢÐ¾

-0.25

 """↵↵

-0.24

endra

-0.24

 crackers

-0.24

POSITIVE LOGITS

æĳĦ

0.32

èµ·æŃ¥

0.28

las

0.26

ç¯ģ

0.24

åŃ£åº¦

0.24

BSD

0.24

ä¾¯

0.24

zas

0.24

/thread

0.24

č↵↵

0.24

Activations Density 0.001%

which

No Comments

No Known Activations