INDEX

Explanations

ator

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

çĽ¹

-0.25

 superClass

-0.25

ä¸Ģåī¯

-0.25

 propName

-0.24

vid

-0.24

æĶ¿çŃĸæİªæĸ½

-0.24

",(

-0.24

èģĮä¸ļæĬĢèĥ½

-0.24

.".

-0.23

.guard

-0.23

POSITIVE LOGITS

åĺ´éĩĮ

0.30

 only

0.27

æĻĴ

0.27

ander

0.26

-append

0.26

åĲŀ

0.26

abile

0.25

å¾Ļ

0.24

ornings

0.24

onder

0.24

Activations Density 0.055%

ator

No Comments

No Known Activations