INDEX

Explanations

Text excerpts

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

å£ĳ

-0.28

Toy

-0.28

orthy

-0.28

 EITHER

-0.25

.po

-0.25

Õ±

-0.23

licable

-0.23

å¾ħ

-0.23

å²³

-0.23

osemite

-0.23

POSITIVE LOGITS

 informational

0.31

ban

0.27

 pipes

0.27

NO

0.26

ISTER

0.25

è¯¢éĹ®

0.25

æ¨¡ç³Ĭ

0.25

NO

0.24

imen

0.24

 fuzzy

0.24

Activations Density 0.000%

Text excerpts

No Comments

No Known Activations