INDEX

Explanations

0

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

 presup

-0.27

 beyond

-0.27

 requirement

-0.24

 requirements

-0.24

 jobs

-0.24

arkin

-0.24

 characteristic

-0.24

æĪĲåĪĨ

-0.24

 Laura

-0.24

rong

-0.23

POSITIVE LOGITS

Ð¸ÑĩÐ½Ð¾

0.28

æ¦ľ

0.27

ymm

0.27

COPE

0.27

?,?,

0.26

ç»Īèº«

0.26

ÑĩÐµÐ¼

0.26

èķī

0.25

SSIP

0.25

Ä±c

0.25

Activations Density 0.016%

0

No Comments

No Known Activations