INDEX

Explanations

cooking instructions

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

 desn

-0.30

ä¸įå¼Ģ

-0.29

æĸ¹ãģ«

-0.27

SM

-0.25

SM

-0.25

 Brill

-0.25

ä¹Łä¸įæĥ³

-0.24

 Aerospace

-0.24

idence

-0.24

HMS

-0.24

POSITIVE LOGITS

 rings

0.26

dbuf

0.25

 scales

0.25

-Jun

0.25

 peel

0.25

rez

0.25

eth

0.25

ALER

0.24

 storms

0.24

ring

0.24

Activations Density 0.001%

cooking instructions

No Comments

No Known Activations