INDEX

Explanations

and

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

omid

-0.28

åĲįåĪĹ

-0.27

 mounting

-0.26

Fut

-0.26

 trenches

-0.25

åĲ¯

-0.25

ER

-0.25

 Tunnel

-0.24

æ¶Ľ

-0.24

reno

-0.24

POSITIVE LOGITS

angep

0.32

andise

0.30

leep

0.27

ock

0.26

ANGED

0.26

æķ´

0.26

èĶŁ

0.24

wine

0.24

orage

0.24

çģµæ´»

0.24

Activations Density 0.003%

and

No Comments

No Known Activations