INDEX

Explanations

suspected

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

éĢģç»Ļ

-0.28

 passe

-0.27

 vÅ©

-0.26

quat

-0.25

Ree

-0.25

ç¦»

-0.25

Ã¡t

-0.25

ure

-0.25

uyáº¿t

-0.25

 Pron

-0.24

POSITIVE LOGITS

Closed

0.28

_extent

0.26

 Closed

0.26

Installer

0.26

aroo

0.24

åĪª

0.24

æĵ¦æĭŃ

0.24

Tower

0.23

 Alternate

0.23

 Allowed

0.23

Activations Density 0.054%

suspected

No Comments

No Known Activations