INDEX

Explanations

sometimes

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

åºĵéĩĮ

-0.29

VID

-0.27

!]

-0.27

.Undef

-0.26

æ¯«æĹł

-0.26

 ÑĦÐ°Ð¹

-0.26

!*

-0.26

[_

-0.25

abel

-0.25

against

-0.24

POSITIVE LOGITS

verige

0.30

 Indo

0.27

xcd

0.27

tg

0.26

éĻĲå®ļ

0.24

NOR

0.24

nor

0.23

GT

0.23

Highlights

0.23

 Personal

0.23

Activations Density 0.003%

sometimes

No Comments

No Known Activations