INDEX

Explanations

better

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

onium

-0.28

atÃ³

-0.28

endum

-0.27

åħ³éĹ¨

-0.25

å®¶è£ħ

-0.25

Ha

-0.25

å«ļ

-0.25

 synth

-0.24

åĨįè§ģ

-0.24

ZIP

-0.24

POSITIVE LOGITS

éļıæĹ¶

0.28

ogie

0.25

 swore

0.25

cio

0.25

 Broncos

0.25

 suá»ĳt

0.24

ä»»ä½ķä¸Ģä¸ª

0.23

èģĨ

0.23

å£«

0.23

éļ¶å±ŀäºİ

0.23

Activations Density 0.013%

better

No Comments

No Known Activations