INDEX

Explanations

Mentions of the name Mark

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

 Prob

-0.27

ëŀµ

-0.26

&_

-0.26

å¥Ħ

-0.25

aea

-0.25

imeo

-0.25

åĭĿ

-0.25

èĥľåĪ©

-0.24

èĽĶ

-0.24

Prob

-0.24

POSITIVE LOGITS

 endif

0.31

getic

0.28

å°½

0.27

Forget

0.27

(exports

0.26

é¸¡æ±¤

0.26

TEL

0.26

endif

0.25

eni

0.24

ovic

0.24

Activations Density 0.004%

Mentions of the name Mark

No Comments

No Known Activations