INDEX

Explanations

Sex and gender

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Lu

-0.26

-su

-0.26

owie

-0.25

 Aires

-0.25

lu

-0.25

nu

-0.25

->[

-0.25

opoly

-0.24

autop

-0.24

hw

-0.24

POSITIVE LOGITS

äºĭåħĪ

0.28

 SINGLE

0.27

sla

0.26

clas

0.25

_FRONT

0.25

tsl

0.24

 slic

0.24

éĺĢ

0.23

 ApiController

0.23

 Strateg

0.23

Activations Density 1.161%

Sex and gender

No Comments

No Known Activations