INDEX

Explanations

Code snippets

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

tab

-0.26

Nor

-0.26

specifier

-0.25

 Scri

-0.24

å®¶åĽŃ

-0.24

_modified

-0.23

tab

-0.23

flo

-0.23

 specifier

-0.23

atory

-0.23

POSITIVE LOGITS

éŀĺ

0.27

æŀģéĻĲ

0.27

æŃ§

0.27

åĲĪæ³ķ

0.26

æĹ¶éĹ´ä¸º

0.25

è¶Ĭ

0.25

æ¦Ĥå¿µ

0.25

/exec

0.25

 mind

0.25

Revenue

0.24

Activations Density 0.060%

Code snippets

No Comments

No Known Activations