INDEX

Explanations

Prepositions and commas

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

substr

-0.28

 substrate

-0.27

 substr

-0.27

 StringComparison

-0.26

hl

-0.25

è¿Ļç§įæĸ¹æ³ķ

-0.25

bject

-0.25

 bible

-0.24

hb

-0.24

Suc

-0.24

POSITIVE LOGITS

igu

0.29

çļĦèĢģ

0.26

æ¸ħåįķ

0.26

RAD

0.26

gest

0.26

åıĪå¥½

0.26

æĥĳ

0.25

ORM

0.25

edy

0.25

åĪĹä¸º

0.25

Activations Density 2.513%

Prepositions and commas

No Comments

No Known Activations