INDEX

Explanations

such

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

cast

-0.27

 increment

-0.25

æīĵæ³ķ

-0.25

%@

-0.25

SSION

-0.25

Cast

-0.24

 cast

-0.24

å®¡è®®éĢļè¿ĩ

-0.24

 viable

-0.24

omp

-0.24

POSITIVE LOGITS

åºĬä¸Ĭ

0.25

åľ¨åºĬä¸Ĭ

0.24

anuts

0.24

amba

0.23

otate

0.23

éŃĳ

0.23

ä¸ĢèĪ¬éĥ½æĺ¯

0.23

ä¸įåĩºæĿ¥

0.23

Bs

0.23

bre

0.23

Activations Density 0.014%

such

No Comments

No Known Activations