INDEX

Explanations

causality

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¿Ļå¯¹äºİ

-0.55

çļĦéĩįè¦ģæĢ§

-0.54

æľīåĬ©äºİ

-0.50

è¿Ļå¯¹

-0.46

æľīåĪ©äºİ

-0.45

 Benefits

-0.44

åįģåĪĨéĩįè¦ģ

-0.42

çļĦåį±å®³

-0.42

 benefits

-0.41

æľīçĽĬ

-0.41

POSITIVE LOGITS

pl

0.30

 unpl

0.28

pl

0.26

egot

0.26

 cred

0.26

verb

0.26

-pl

0.25

æ¯ĶæĭŁ

0.25

 bill

0.25

å¹³åİŁ

0.25

Activations Density 0.001%

causality

No Comments

No Known Activations