INDEX

Explanations

1

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 battlefield

-0.32

èį»

-0.28

ara

-0.27

argon

-0.27

Strings

-0.26

ocity

-0.26

 Tested

-0.25

UnderTest

-0.25

 ÑĦÐ¾ÑĢÑĥÐ¼

-0.24

æī¹åĩĨ

-0.24

POSITIVE LOGITS

rive

0.28

è§Ĩ

0.27

æ¶µçĽĸ

0.26

çĶ»

0.26

è¦Ĩ

0.26

erview

0.25

jaw

0.25

è§¦

0.25

åĶ±

0.25

Vul

0.25

Activations Density 0.001%

1

No Comments

No Known Activations