INDEX

Explanations

sitting/training/equipment

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-master

-0.27

 detailed

-0.27

usz

-0.27

aster

-0.26

 Detailed

-0.25

 complete

-0.24

alyze

-0.24

Detailed

-0.24

iesz

-0.24

Suffix

-0.23

POSITIVE LOGITS

 lick

0.28

å¾Ĵ

0.28

ties

0.27

nings

0.27

äº²

0.27

ither

0.27

ç»ıè¿ĩ

0.27

bers

0.25

æ´ĩ

0.25

 BASIS

0.25

Activations Density 0.007%

sitting/training/equipment

No Comments

No Known Activations