INDEX

Explanations

Programming code

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

 fame

-0.33

åı«

-0.27

åıĪå¥½

-0.26

çī¹çĤ¹

-0.25

otypes

-0.25

å¯Ĵ

-0.25

æ½ľåĬĽ

-0.24

 schemas

-0.24

atisfaction

-0.24

 Paper

-0.24

POSITIVE LOGITS

 trá»Ŀi

0.25

adero

0.24

è¿Łè¿Ł

0.24

 minded

0.24

è¢¢

0.24

iddy

0.24

personal

0.23

aml

0.23

.makeText

0.23

 cess

0.23

Activations Density 0.000%

Programming code

No Comments

No Known Activations