INDEX

Explanations

the and questions

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

apas

-0.34

å¿į

-0.33

iya

-0.30

apa

-0.28

iel

-0.28

quisite

-0.27

IEL

-0.26

åĺ´

-0.26

uil

-0.25

å²Ĳ

-0.24

POSITIVE LOGITS

 cabe

0.32

orent

0.29

.appspot

0.27

æĶ¯éħį

0.26

_DIRECT

0.26

 leadership

0.25

soever

0.25

isu

0.24

éĵħ

0.24

Dob

0.23

Activations Density 0.000%

the and questions

No Comments

No Known Activations