INDEX

Explanations

Numbers

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

é¦

-0.27

%(

-0.26

%%

-0.25

æĮīè§Ħå®ļ

-0.25

 recorded

-0.25

ingt

-0.25

ogenerated

-0.24

Experts

-0.24

%%

-0.24

Ã©r

-0.24

POSITIVE LOGITS

icut

0.28

versions

0.27

 hybrids

0.25

 TypeName

0.24

ane

0.24

 alike

0.24

éĹ²ç½®

0.24

assembly

0.24

 histories

0.24

 assembly

0.24

Activations Density 0.002%

Numbers

No Comments

No Known Activations