INDEX

Explanations

Articles or guidance

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

irez

-0.33

ä¹¾

-0.30

 unic

-0.28

 Ð¾Ð±ÑĢÐ°Ð·Ð¾Ð¼

-0.28

ç®§

-0.27

onom

-0.27

URAL

-0.26

 Bedrooms

-0.25

é¸±

-0.25

dr

-0.25

POSITIVE LOGITS

leÅŁ

0.28

MPS

0.28

trÃ¤

0.27

 groupId

0.26

æľŁ

0.25

æ¦Ĥå¿µèĤ¡

0.25

çĥ«

0.24

è¾¨

0.24

Ã¤m

0.24

 bible

0.23

Activations Density 0.002%

Articles or guidance

No Comments

No Known Activations