INDEX

Explanations

computer configuration files

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 conveniently

-0.27

æĪĲè´¥

-0.26

æĪ²

-0.26

æ»ĩ

-0.26

è¿ĳè§Ĩ

-0.25

arily

-0.25

emade

-0.24

 cá»©u

-0.24

è¿½è¸ª

-0.23

æ¹ĸåĮº

-0.23

POSITIVE LOGITS

æĦıåĲĳ

0.29

GLOBALS

0.29

iations

0.27

 Third

0.26

 third

0.26

ä¸īçº§

0.26

ragen

0.25

æķıæĦŁ

0.24

Prov

0.24

eve

0.23

Activations Density 0.001%

computer configuration files

No Comments

No Known Activations