INDEX

Explanations

code and identifiers

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

 later

-0.34

åĲİæĿ¥

-0.32

åĲİç»Ń

-0.29

 subsequent

-0.27

ä»¥åĲİ

-0.27

 fetch

-0.26

 future

-0.26

æĹ¥åĲİ

-0.26

olars

-0.26

å½ĵæĹ¶çļĦ

-0.25

POSITIVE LOGITS

ä¸Ľä¹¦

0.26

/OR

0.26

INCLUDE

0.25

-history

0.24

-highlight

0.24

/pp

0.24

åĪį

0.23

.azure

0.23

 roman

0.23

pb

0.23

Activations Density 0.000%

code and identifiers

No Comments

No Known Activations