INDEX

Explanations

and

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

 blinded

-0.28

ä¼ļè§īå¾Ĺ

-0.27

 initialised

-0.26

 addCriterion

-0.26

åĬłæĭ¿

-0.26

 initialise

-0.25

ä¸Ģå¯¹

-0.25

ëįĺ

-0.24

 Ãºlt

-0.24

æĦŁè§īåĪ°

-0.24

POSITIVE LOGITS

TAR

0.27

ichert

0.26

ãĤ¸ãĥ¼

0.26

curl

0.24

=end

0.24

addle

0.24

Stretch

0.24

sim

0.23

 sequ

0.23

ector

0.23

Activations Density 0.013%

and

No Comments

No Known Activations