INDEX

Explanations

test

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

.expect

-0.29

åĹħ

-0.28

uten

-0.26

ä¸īä½įä¸Ģä½ĵ

-0.26

ä½ĵç§¯

-0.26

quiv

-0.25

-Mail

-0.25

letic

-0.25

è¹Ń

-0.24

ëł¨

-0.24

POSITIVE LOGITS

 overst

0.27

 Locator

0.27

**

0.25

åĩºåİĤ

0.24

 getClass

0.24

 locator

0.24

æİ¨åĩºçļĦ

0.24

 Rupert

0.23

mort

0.23

Fort

0.23

Activations Density 0.001%

test

No Comments

No Known Activations