INDEX

Explanations

article excerpts

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

æĢİä¹Īæł·

-0.30

åģļä»Ģä¹Ī

-0.27

 interpreter

-0.26

yny

-0.26

è¯Ń

-0.25

æĻºæħ§

-0.25

ä¸įç¦ģ

-0.25

interpreter

-0.25

cline

-0.25

ysz

-0.24

POSITIVE LOGITS

les

0.25

ë°°

0.25

rtle

0.25

lore

0.24

Ð°ÑĢÐ°Ð¼

0.24

é«ĺæ½®

0.24

ibre

0.23

spath

0.23

é«ħ

0.23

åĿ¯

0.23

Activations Density 0.003%

article excerpts

No Comments

No Known Activations