INDEX

Explanations

code and memory safety

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

 Wend

-0.25

 Amid

-0.25

æµ£

-0.25

è¾¨

-0.24

åģķ

-0.24

æµ´å®¤

-0.24

çº§ä»¥ä¸Ĭ

-0.23

Domin

-0.23

 cherry

-0.23

 Rank

-0.23

POSITIVE LOGITS

×ķ×¨×ļ

0.27

.shtml

0.25

PositiveButton

0.25

çĽ²

0.24

cdc

0.24

eline

0.24

rna

0.23

fed

0.23

ä¼¤åı£

0.23

ingly

0.23

Activations Density 0.002%

code and memory safety

No Comments

No Known Activations