INDEX

Explanations

Mixed document snippets

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĽĨ

-0.31

çıŃ

-0.30

(clicked

-0.29

æľ¬ç«Ļ

-0.28

inct

-0.28

é¢Ī

-0.27

ry

-0.25

.DriverManager

-0.24

åŁ

-0.24

stdexcept

-0.24

POSITIVE LOGITS

 feedback

0.28

jes

0.27

 grounded

0.26

feedback

0.25

åıĺä¸º

0.25

wij

0.25

tru

0.24

 Ð¿Ñģ

0.24

[{'

0.24

Ws

0.24

Activations Density 0.825%

Mixed document snippets

No Comments

No Known Activations