INDEX

Explanations

hypothetical questions

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

iese

-0.27

é©±åĬ¨

-0.27

adel

-0.26

 ModelState

-0.26

é¦

-0.26

æ¡¥

-0.26

é©

-0.25

_bridge

-0.25

buc

-0.25

Wh

-0.24

POSITIVE LOGITS

Withdraw

0.28

_BITMAP

0.26

çļĦå¥³äºº

0.26

"..

0.25

/owl

0.25

ermen

0.25

åĪ»èĭ¦

0.24

 Consort

0.24

çļĦçĶ·äºº

0.24

 quem

0.24

Activations Density 0.004%

hypothetical questions

No Comments

No Known Activations