INDEX

Explanations

is

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çļĦèĦ¸

-0.28

artner

-0.26

 Houses

-0.26

.blogspot

-0.25

 Deployment

-0.25

 aÃ§Ä±l

-0.25

CW

-0.25

limitations

-0.24

Ø¹ÙĦØ§

-0.23

 Univ

-0.23

POSITIVE LOGITS

sequent

0.28

Whether

0.26

whether

0.26

obi

0.25

iki

0.25

 whether

0.25

ä¸ĭéĿ¢æĺ¯å°ı

0.24

äºĴèģĶäºĴéĢļ

0.24

ckt

0.24

 ghost

0.24

Activations Density 0.009%

is

No Comments

No Known Activations