INDEX

Explanations

assistant

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

ÅĽcie

-0.29

èĢ³

-0.26

åĪĹ

-0.26

klÃ¤

-0.26

omething

-0.26

iated

-0.26

Ø¹Ø¨

-0.26

 Shock

-0.25

yb

-0.25

ighted

-0.25

POSITIVE LOGITS

_control

0.25

ustr

0.25

utor

0.25

å¯¹æĪĳè¯´

0.25

arts

0.25

 Autor

0.25

 Zoom

0.24

 controlled

0.24

ount

0.24

æ»¥çĶ¨

0.24

Activations Density 0.063%

assistant

No Comments

No Known Activations