INDEX

Explanations

Technical or organizational information

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hk

-0.30

incy

-0.30

ants

-0.27

à¸Ĳ

-0.26

æĮīè§Ħå®ļ

-0.26

buster

-0.25

Ð±ÑĭÑĤ

-0.25

ANCH

-0.25

HIP

-0.25

NAN

-0.25

POSITIVE LOGITS

ilitation

0.28

chner

0.24

ccione

0.24

urray

0.24

 dÃ©l

0.24

isl

0.24

æĶ¾è¿ĩ

0.24

ãĤ¹ãĥĪãĥ¬ãĤ¹

0.23

imensional

0.23

TeX

0.23

Activations Density 0.001%

Technical or organizational information

No Comments

No Known Activations