INDEX

Explanations

Q&A forum text

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mony

-0.26

 bast

-0.25

æĸĹ

-0.23

ä¸įå¦¨

-0.22

 Ellis

-0.22

åŃ¦éĹ®

-0.22

virtual

-0.22

eny

-0.22

airie

-0.22

 dataSnapshot

-0.22

POSITIVE LOGITS

_normalized

0.26

èĭį

0.25

ç»ĻåĬĽ

0.25

 Registr

0.25

Con

0.25

eworld

0.25

éªĮ

0.24

ousands

0.24

 Conditional

0.24

Con

0.23

Activations Density 0.508%

Q&A forum text

No Comments

No Known Activations