INDEX

Explanations

reflexive pronouns

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

Dil

-0.27

è±¡

-0.26

åĪ°è´¦

-0.25

 Ð²ÐµÐº

-0.25

çĤ¹æ»´

-0.25

åĢ¡

-0.24

èĲ½

-0.24

erg

-0.24

æĽĿ

-0.24

sWith

-0.24

POSITIVE LOGITS

@email

0.28

 forks

0.26

 lesser

0.26

ocio

0.25

åįģåĪĨ

0.25

è¿Ľåĩº

0.25

 Lesser

0.25

 Contributor

0.24

 intimately

0.24

 Economist

0.23

Activations Density 0.956%

reflexive pronouns

No Comments

No Known Activations