INDEX

Explanations

organizations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çļĦæľīæķĪ

-0.28

ool

-0.27

å¤Ķ

-0.26

 reck

-0.25

eline

-0.24

die

-0.24

é©º

-0.23

éĩıäº§

-0.23

.putExtra

-0.23

çļĦçĽ¸åħ³

-0.23

POSITIVE LOGITS

rico

0.27

ewise

0.27

ä¸Ģåı£æ°Ķ

0.27

nite

0.26

Fonts

0.25

æĪĳéĥ½

0.25

chio

0.24

GP

0.24

é«ĺä»·

0.23

upro

0.23

Activations Density 45.268%

organizations

No Comments

No Known Activations