INDEX

Explanations

scientific/programming text

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

 initials

-0.30

_PKT

-0.26

otted

-0.26

ogo

-0.26

 initially

-0.25

Ãłi

-0.25

wed

-0.24

 pharm

-0.24

 Sector

-0.24

 ÅŁekil

-0.24

POSITIVE LOGITS

éĶ¥

0.28

 hookup

0.28

 incontro

0.27

tical

0.27

thon

0.24

çŃĭ

0.24

AFE

0.24

åĬ²

0.24

essian

0.24

coop

0.24

Activations Density 0.025%

scientific/programming text

No Comments

No Known Activations