INDEX

Explanations

ron

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

 tails

-0.31

å¦¾

-0.29

([[

-0.28

çĥŃæĴŃ

-0.28

tails

-0.27

PROTO

-0.25

Ļ¶

-0.24

Ã¤ch

-0.24

 tail

-0.23

/link

-0.23

POSITIVE LOGITS

å·¢

0.26

ä¸¾ä¾ĭ

0.25

nton

0.25

 remote

0.24

Campaign

0.24

getValue

0.24

 diarr

0.23

Ø¡

0.23

 extracted

0.23

oun

0.23

Activations Density 0.027%

ron

No Comments

No Known Activations