INDEX

Explanations

helmet

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

itat

-0.28

å´ĸ

-0.27

çĥĪå£«

-0.26

locker

-0.26

packed

-0.25

ç¬¬ä¸ĢæĿ¡

-0.25

ç¥¨

-0.25

_documents

-0.24

NECT

-0.24

ensen

-0.24

POSITIVE LOGITS

 Presence

0.29

 presenÃ§a

0.26

 familiarity

0.26

nah

0.25

Presence

0.25

æĤ¬

0.25

prÃ©s

0.25

 Appointment

0.24

room

0.24

 StatusBar

0.24

Activations Density 0.053%

helmet

No Comments

No Known Activations