INDEX

Explanations

garment

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

notated

-0.25

ba

-0.25

æĮº

-0.24

æİ¥åĲ¬

-0.24

iform

-0.24

PTY

-0.23

lement

-0.23

APSHOT

-0.23

acements

-0.23

ITIVE

-0.23

POSITIVE LOGITS

Cong

0.27

allis

0.24

StringUtil

0.24

 Congratulations

0.23

 paso

0.23

 secretary

0.23

altar

0.23

busters

0.23

 Cong

0.22

Tro

0.22

Activations Density 0.506%

garment

No Comments

No Known Activations