INDEX

Explanations

adjectives

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

otypes

-0.30

reet

-0.27

ovo

-0.27

åĲĮä¸Ģ

-0.27

otype

-0.25

çĶ°

-0.25

èµŀ

-0.25

ç»³

-0.24

è·Ŀ

-0.24

éļĽ

-0.24

POSITIVE LOGITS

ity

0.31

æīĢæıĲä¾Ľä¹ĭ

0.30

ities

0.29

ness

0.29

 while

0.28

izedName

0.28

idade

0.28

ITY

0.28

IDADE

0.26

 pending

0.26

Activations Density 0.023%

adjectives

No Comments

No Known Activations