INDEX

Explanations

Names and locations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UGHT

-0.26

ught

-0.25

 Main

-0.25

 computer

-0.24

æĸ¹åľĨ

-0.24

uar

-0.24

.ByteArray

-0.23

Rt

-0.23

ĳľ

-0.23

 Hastings

-0.23

POSITIVE LOGITS

ç»¼åĲĪä½ĵ

0.26

organisation

0.26

 Shiv

0.26

 organis

0.25

ä¸įç»ı

0.25

å¤ľ

0.24

AMI

0.24

æĪĲä»½

0.24

nob

0.24

awy

0.24

Activations Density 0.003%

Names and locations

No Comments

No Known Activations