INDEX

Explanations

Likewise

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

%+

-0.28

 tweaked

-0.27

æ¹

-0.25

yet

-0.25

 tweak

-0.25

hed

-0.24

 mocked

-0.23

é¢Īéĥ¨

-0.23

èĽ®

-0.23

 cheaper

-0.23

POSITIVE LOGITS

chie

0.30

èĥİ

0.27

 fores

0.27

ãĤĦãĤĬ

0.26

urch

0.25

æĹ©

0.25

abilia

0.24

asto

0.24

terra

0.24

$fdata

0.24

Activations Density 0.004%

Likewise

No Comments

No Known Activations