INDEX

Explanations

his

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

irse

-0.27

icamente

-0.27

Ð°Ð»ÑĮÐ½Ð¾

-0.26

antly

-0.26

allee

-0.26

ä¸įæŃ»

-0.25

=https

-0.25

Regressor

-0.25

 Matches

-0.24

POSITIVE LOGITS

 Proxy

0.28

Attrib

0.27

ãĤ¢ãĤ¤

0.26

Rib

0.25

proxy

0.25

attrib

0.25

åĲ¸å¼ķåĬĽ

0.25

 proxy

0.25

 Convenient

0.24

.high

0.24

Activations Density 0.001%

his

No Comments

No Known Activations