INDEX

Explanations

My

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

iffs

-0.29

ç½ĳéĢļ

-0.26

æĪĺæľº

-0.26

uard

-0.25

ä¸įéĶĻ

-0.25

 coupe

-0.24

riages

-0.24

icket

-0.24

ully

-0.23

andle

-0.22

POSITIVE LOGITS

PIO

0.35

 arte

0.29

PIO

0.27

phas

0.26

 Purple

0.25

çĶ»çĶ»

0.25

æ¹ĸ

0.24

 mÃ³

0.24

omer

0.24

.imgur

0.24

Activations Density 0.031%

My

No Comments

No Known Activations