INDEX

Explanations

Excerpts, various sources

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

iar

-0.26

æľĢ

-0.26

âĨ©

-0.25

 Kunden

-0.24

entrant

-0.24

èĢħçļĦ

-0.24

=en

-0.24

 lugar

-0.23

 Brennan

-0.23

íĽĪ

-0.23

POSITIVE LOGITS

 mask

0.31

mask

0.30

Mask

0.29

 Mask

0.29

.mask

0.29

à¸ģà¸²à¸£à¸Ĺà¸³

0.26

 queryString

0.26

æ±ľ

0.26

 masked

0.25

masked

0.24

Activations Density 0.001%

Excerpts, various sources

No Comments

No Known Activations