INDEX

Explanations

headed

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

æ¡ħ

-0.29

 remote

-0.26

Mik

-0.25

ä¸įä¸Ĭ

-0.25

 getWindow

-0.25

UID

-0.24

reed

-0.23

 Lions

-0.23

æī¹ç¤º

-0.23

 Bair

-0.23

POSITIVE LOGITS

rott

0.26

æĮŀ

0.25

ÑĮ

0.25

Ð°ÑģÑģ

0.25

_FAULT

0.25

 Hemisphere

0.25

otte

0.24

æĲħ

0.24

obb

0.24

Fault

0.24

Activations Density 45.171%

headed

No Comments

No Known Activations