INDEX

Explanations

confuse

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

>[]

-0.27

 compose

-0.25

.Automation

-0.25

&action

-0.24

è¿ĻæĦıåĳ³çĿĢ

-0.23

 automate

-0.23

_Selection

-0.23

automation

-0.23

'post

-0.23

.sav

-0.23

POSITIVE LOGITS

éĿ¡

0.28

ling

0.26

ugg

0.26

abouts

0.26

 digs

0.25

del

0.25

åħľ

0.25

kers

0.24

æł¼

0.24

 mined

0.24

Activations Density 0.219%

confuse

No Comments

No Known Activations