INDEX

Explanations

code comments

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

 DÃ¼

-0.28

 SUBJECT

-0.27

Subjects

-0.27

Ã¤nn

-0.26

ãģĤãģ¾ãĤĬ

-0.26

æĮ½

-0.25

ewire

-0.25

ignKey

-0.25

ervoir

-0.24

abela

-0.24

POSITIVE LOGITS

~-

0.28

HG

0.27

clist

0.26

æ²¦

0.26

å´ĸ

0.26

æ³·

0.26

apolis

0.26

fug

0.25

WG

0.25

tero

0.24

Activations Density 0.145%

code comments

No Comments

No Known Activations