INDEX

Explanations

order/comparison

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enal

-0.30

oric

-0.29

elts

-0.26

riers

-0.26

inges

-0.25

reeNode

-0.25

hift

-0.24

omers

-0.24

loat

-0.24

oseconds

-0.24

POSITIVE LOGITS

 scenario

0.31

 situation

0.30

set

0.30

ä¸Ģä¸Ģ

0.29

 group

0.27

è¿Ľç¨ĭä¸Ń

0.27

mod

0.27

æĥħåĨµ

0.26

scenario

0.26

æĥħå½¢

0.26

Activations Density 0.039%

order/comparison

No Comments

No Known Activations