INDEX

Explanations

't

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

ä»¥èī²

-0.31

otto

-0.27

kus

-0.26

||(

-0.24

 rocker

-0.24

_il

-0.24

á»Ĵ

-0.24

hq

-0.23

acker

-0.23

ä¼İ

-0.23

POSITIVE LOGITS

inta

0.28

 doctrine

0.27

çĤī

0.27

ìŀĩ

0.26

æĭħå¿ĥ

0.25

çļĦè¯´æ³ķ

0.24

 collecting

0.24

_constants

0.24

 Doctrine

0.24

å¤§éĺŁ

0.24

Activations Density 0.016%

't

No Comments

No Known Activations