INDEX

Explanations

Enumeration/Components

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

_traits

-0.28

iants

-0.27

ials

-0.26

iano

-0.25

æ½¢

-0.24

ä¸Ńå¿ĥåŁİå¸Ĥ

-0.24

èĢĥãģĪãĤĭ

-0.24

(reference

-0.23

chodzÄħ

-0.23

ALLY

-0.23

POSITIVE LOGITS

åĮ¿

0.30

çĩĥçĥ§

0.29

æľĢåĲİ

0.27

ç²ĺ

0.26

è¿Ļä¹Īåģļ

0.25

çĩĥ

0.25

ocode

0.25

å¿ĥåĬ¨

0.25

åľ°ä¸ĭå®¤

0.24

idf

0.24

Activations Density 0.001%

Enumeration/Components

No Comments

No Known Activations