INDEX

Explanations

code, technical documentation

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

ä¸įåĪĨ

-0.28

éĴ³

-0.26

çŀħ

-0.26

âĿ®

-0.26

bit

-0.25

éĢĽ

-0.25

attended

-0.25

 prat

-0.25

:nil

-0.24

bit

-0.24

POSITIVE LOGITS

ovel

0.28

/posts

0.26

ogr

0.25

izz

0.25

iz

0.25

 responsibility

0.24

_FEED

0.24

ewood

0.24

ror

0.24

ep

0.23

Activations Density 0.004%

code, technical documentation

No Comments

No Known Activations