INDEX

Explanations

suddenly

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

digest

-0.32

 digest

-0.27

 Digest

-0.24

éĩįè¦ģåĨħå®¹

-0.24

Ð´ÑĥÐ¼

-0.24

 balances

-0.24

Digest

-0.24

æĸ¹ä¾¿

-0.23

 knowledge

-0.23

igest

-0.23

POSITIVE LOGITS

 glove

0.27

å¸Ń

0.27

ssue

0.25

veh

0.25

æĪ¡

0.25

ivos

0.25

celed

0.24

ically

0.24

 ally

0.24

çĸı

0.24

Activations Density 0.003%

suddenly

No Comments

No Known Activations