INDEX

Explanations

computer code/markup

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

Difficulty

-0.29

acen

-0.28

 difficulty

-0.27

 Difficulty

-0.27

BUFFER

-0.27

-0.25

 area

-0.25

éĢı

-0.25

 AREA

-0.24

bara

-0.24

POSITIVE LOGITS

æĿĥ

0.29

æ¨¯

0.28

animation

0.27

ë¡±

0.26

æĮ½

0.25

çİ©åħ·

0.25

é©¬åĬĽ

0.25

ãĥ¼ãĥ³

0.25

-inst

0.25

 dreams

0.25

Activations Density 0.007%

computer code/markup

No Comments

No Known Activations