INDEX

Explanations

one

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

urved

-0.26

ewn

-0.26

 reun

-0.26

TimeString

-0.25

.SP

-0.25

'options

-0.25

ypad

-0.25

 convinced

-0.24

jax

-0.24

ECH

-0.24

POSITIVE LOGITS

è´¡çĮ®

0.27

è¾«

0.26

isi

0.25

åľ³

0.24

çħ§

0.24

ê²¬

0.24

æİ¨åĲĳ

0.24

Overlap

0.24

åĪºæ¿Ģ

0.24

 WITHOUT

0.23

Activations Density 0.012%

one

No Comments

No Known Activations