INDEX

Explanations

Code and math problems

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĺ¯æĪĳä»¬

-0.29

-history

-0.28

ETY

-0.27

odu

-0.27

åĨī

-0.26

çļĦåİĨåı²

-0.25

ä¹ŁæĽ¾

-0.24

deps

-0.24

orro

-0.24

è¿Ļæĺ¯æĪĳä»¬

-0.24

POSITIVE LOGITS

 Äĳáº§y

0.26

çµľ

0.26

å¤§å®¶

0.25

EQUAL

0.25

ria

0.25

Drive

0.23

 Searches

0.23

==(

0.23

=#

0.23

aterial

0.23

Activations Density 0.009%

Code and math problems

No Comments

No Known Activations