INDEX

Explanations

Figure

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

-side

-0.26

Live

-0.26

Side

-0.26

 Archives

-0.25

Â©

-0.25

 Live

-0.25

live

-0.25

 greeted

-0.24

åıįå¯¹

-0.24

/operators

-0.24

POSITIVE LOGITS

irm

0.29

irim

0.28

+len

0.28

è¢«åĬ¨

0.28

urer

0.26

din

0.26

èĻº

0.25

ç½ĳè®¯

0.25

efined

0.24

ToF

0.24

Activations Density 0.004%

Figure

No Comments

No Known Activations