INDEX

Explanations

Abbreviations

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

Negative Logits

-0.40

-0.35

-0.33

rz

-0.33

sin

-0.32

sing

-0.30

sist

-0.29

ed

-0.28

ei

-0.28

 domic

-0.28

POSITIVE LOGITS

ÑģÑĤÐ°Ð²Ð¸ÑĤÑĮ

0.31

plier

0.27

å¡ĳ

0.26

abh

0.25

beiter

0.25

pliers

0.24

atten

0.24

puted

0.23

 Crunch

0.23

oucher

0.23

Activations Density 0.034%

Abbreviations

No Known Activations