INDEX

Explanations

patient/patients

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

ilio

-0.27

redi

-0.27

nah

-0.26

éķ¿çº¦

-0.26

_press

-0.26

 cuanto

-0.25

 UnityEditor

-0.24

æĩ

-0.24

 crÃ©d

-0.24

blink

-0.24

POSITIVE LOGITS

iets

0.28

even

0.27

Even

0.27

ç»Ħç»ĩå®ŀæĸ½

0.26

éĺŁåĳĺ

0.26

ä¸»æĮģäºº

0.25

 even

0.25

rogram

0.24

Case

0.24

çŃīæĥħåĨµ

0.24

Activations Density 0.010%

patient/patients

No Comments

No Known Activations