INDEX

Explanations

multiple languages

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ahi

-0.31

berra

-0.29

onis

-0.29

 Disp

-0.26

 Bureau

-0.25

 batchSize

-0.25

.SetValue

-0.25

ÑĢÐ¾Ð¶

-0.24

åĽ¢è´Ń

-0.24

 glUniform

-0.24

POSITIVE LOGITS

á»ĩm

0.26

ãĥ§ãĥ³

0.25

æĥ³å¿µ

0.25

BOT

0.24

åĻ¨

0.24

 thereafter

0.24

 exercising

0.23

anka

0.23

ä¹ī

0.23

é»ĺé»ĺåľ°

0.23

Activations Density 0.005%

multiple languages

No Comments

No Known Activations