INDEX

Explanations

Start of a narrative

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĢļå¸¸

-0.25

me

-0.25

æĪĳåıĪ

-0.24

rou

-0.24

 Normally

-0.24

.ImageLayout

-0.23

opensource

-0.23

 currently

-0.23

å®°

-0.23

 phase

-0.23

POSITIVE LOGITS

 verw

0.26

anse

0.25

acting

0.25

osten

0.25

sil

0.25

_floor

0.24

OTA

0.24

æĽĿåħī

0.24

Pel

0.23

 basics

0.23

Activations Density 0.002%

Start of a narrative

No Comments

No Known Activations