INDEX

Explanations

Parm

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

 rode

-0.29

aptcha

-0.26

tesy

-0.25

rem

-0.25

à¸¤

-0.24

å¹ķ

-0.24

mob

-0.24

ilog

-0.24

ä½Ľ

-0.24

 wards

-0.24

POSITIVE LOGITS

stamp

0.30

(sig

0.30

åİĤåĮº

0.28

ä¸įè§£

0.27

enqueue

0.27

sig

0.27

baugh

0.26

.sig

0.26

DataStream

0.26

é¤Ĳåİħ

0.26

Activations Density 0.008%

Parm

No Comments

No Known Activations