INDEX

Explanations

assert

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

MessageType

-0.28

åĺĺ

-0.25

æŀ§

-0.25

æĬľ

-0.25

 watch

-0.25

ocard

-0.25

uations

-0.24

åłĤ

-0.24

yper

-0.24

 âĸĪâĸĪ

-0.24

POSITIVE LOGITS

 clad

0.29

åĲİåĭ¤

0.28

 burgl

0.25

 Claus

0.25

 Props

0.25

 Otherwise

0.25

çĥŃéĶĢ

0.24

-backed

0.24

 attaches

0.24

 PROCUREMENT

0.23

Activations Density 0.604%

assert

No Comments

No Known Activations