INDEX

Explanations

scalp

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

åĿĬ

-0.28

Cob

-0.26

 serr

-0.25

å¥½æ¶Īæģ¯

-0.24

stood

-0.24

ç¡ļ

-0.24

urers

-0.24

 savory

-0.24

unce

-0.24

arb

-0.24

POSITIVE LOGITS

ctl

0.31

CHA

0.26

æĸĭ

0.26

 witnessing

0.26

æĴ

0.25

ä¸¤çĤ¹

0.25

 setup

0.25

æĶ»

0.25

ç§°

0.24

å¤ĩä»½

0.24

Activations Density 0.783%

scalp

No Comments

No Known Activations