INDEX

Explanations

Code, documentation, forums

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

tdown

-0.26

oga

-0.25

á»¤

-0.25

plotlib

-0.24

<Unit

-0.24

æ°´

-0.24

obra

-0.24

InView

-0.24

PageRoute

-0.23

upy

-0.23

POSITIVE LOGITS

 corners

0.32

rub

0.28

 rouge

0.28

 colors

0.27

 blanc

0.27

colors

0.26

 colours

0.26

 toes

0.25

é¥®

0.25

Rac

0.24

Activations Density 0.000%

Code, documentation, forums

No Comments

No Known Activations