INDEX

Explanations

rise

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 naked

-0.31

uble

-0.27

èĥ¶

-0.26

-reviewed

-0.26

etto

-0.26

ethe

-0.26

 cá»©

-0.25

 Signs

-0.25

 Brig

-0.24

atures

-0.24

POSITIVE LOGITS

æ²¥

0.26

gulp

0.26

ä¸»ç®¡

0.25

åĪĩãĤĬ

0.25

çĲĽ

0.25

_LAYOUT

0.24

_REGISTRY

0.24

Fay

0.24

æĭ©

0.23

ç¨Ķ

0.23

Activations Density 0.007%

rise

No Comments

No Known Activations