INDEX

Explanations

age

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æįŁèĢĹ

-0.28

plural

-0.27

Fig

-0.26

Penn

-0.26

 minut

-0.26

etri

-0.26

 shin

-0.25

Fig

-0.24

 bá»ģn

-0.24

_ten

-0.24

POSITIVE LOGITS

 fits

0.31

ched

0.29

ariat

0.28

ç¤ģ

0.28

çºłæŃ£

0.28

 fitted

0.27

 fitting

0.26

åģļæ³ķ

0.25

Gos

0.25

alendar

0.25

Activations Density 0.751%

age

No Comments

No Known Activations