INDEX

Explanations

medical studies

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

SEA

-0.26

æĪĲåĬŁçİĩ

-0.25

ARA

-0.25

è¶´

-0.25

ummy

-0.25

pig

-0.25

SEA

-0.24

@Enable

-0.24

pecified

-0.24

adden

-0.24

POSITIVE LOGITS

shapes

0.28

_exports

0.27

åĤµ

0.27

 comm

0.25

leton

0.25

_shapes

0.25

hydration

0.25

eme

0.24

åĢº

0.24

Coder

0.24

Activations Density 2.057%

medical studies

No Comments

No Known Activations