INDEX

Explanations

ing

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aptor

-0.29

CTYPE

-0.26

ç¼º

-0.26

Uns

-0.26

imore

-0.25

åĩĨ

-0.25

æĦŁè§¦

-0.24

 full

-0.24

inden

-0.23

-full

-0.23

POSITIVE LOGITS

è¿Ķ

0.32

edReader

0.30

avern

0.29

ires

0.28

edList

0.27

 terminal

0.26

DOMAIN

0.25

yan

0.25

oden

0.25

yy

0.24

Activations Density 0.005%

ing

No Comments

No Known Activations