INDEX

Explanations

courses

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

 sizing

-0.28

 ming

-0.26

athon

-0.25

åĨ³èĥľ

-0.25

riter

-0.25

 bottoms

-0.25

åºķ

-0.25

å½¢æĢģ

-0.25

anything

-0.24

indow

-0.24

POSITIVE LOGITS

 bush

0.28

éĶĦ

0.28

(parameters

0.27

Bush

0.26

 aides

0.26

-Ass

0.25

 Ð¿Ð¾Ð»ÑĥÑĩÐ°

0.24

 blues

0.23

ourage

0.23

Aliases

0.23

Activations Density 34.148%

courses

No Comments

No Known Activations