INDEX

Explanations

Abbreviations/Anatomy

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

orie

-0.31

illo

-0.30

 IMPLIED

-0.28

risk

-0.26

cox

-0.25

eres

-0.24

SOR

-0.24

ahun

-0.24

entially

-0.23

Risk

-0.23

POSITIVE LOGITS

åĬłå¼º

0.28

addons

0.26

åĸĳ

0.25

ÄĻdzi

0.25

åĬłå¼ºå¯¹

0.25

æĲŀå¥½

0.25

isz

0.23

 solid

0.23

åĬłæ·±

0.23

 suspend

0.23

Activations Density 0.003%

Abbreviations/Anatomy

No Comments

No Known Activations