INDEX

Explanations

Medical and geographical terms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ographies

-0.31

ç¼ī

-0.28

 stri

-0.27

iss

-0.26

 legal

-0.25

æ¢¢

-0.25

)::

-0.25

è´¨

-0.25

iso

-0.24

rif

-0.24

POSITIVE LOGITS

æĲĶ

0.30

 Ã©poca

0.27

æĬĳåĪ¶

0.27

wr

0.26

.dk

0.26

Aliases

0.26

æľŁéĹ´

0.25

æľŁåĨħ

0.25

-period

0.25

FK

0.24

Activations Density 0.002%

Medical and geographical terms

No Comments

No Known Activations