INDEX

Explanations

Code, markup, and foreign languages

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

è´¤

-0.28

-slide

-0.27

ENSOR

-0.26

åĭ¾

-0.26

ICIAL

-0.26

èį¡

-0.26

nds

-0.25

é©³

-0.25

åĳķ

-0.25

 Singles

-0.25

POSITIVE LOGITS

 inclusion

0.27

 kaum

0.25

 arous

0.25

à¸Ħà¸£à¸Ńà¸ļ

0.25

cluded

0.25

Fur

0.23

Vis

0.23

æ¯ıæ¬¡

0.23

áº¥

0.23

uiten

0.23

Activations Density 0.001%

Code, markup, and foreign languages

No Comments

No Known Activations