INDEX

Explanations

changing, improving, creating

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

éĤ£äºº

-0.28

AXB

-0.26

NCY

-0.26

rzy

-0.26

UME

-0.26

(Uri

-0.25

ingham

-0.25

ç½ĳåıĭè¯Ħè®º

-0.24

quila

-0.24

åĮĸè¿Ľç¨ĭ

-0.24

POSITIVE LOGITS

ï¸

0.27

 logical

0.27

 Palo

0.26

æĬ¥ç¤¾

0.25

logical

0.25

åĨł

0.25

 Logical

0.24

olerance

0.24

encies

0.24

æĮģç»Ń

0.24

Activations Density 0.069%

changing, improving, creating

No Comments

No Known Activations