INDEX

Explanations

*

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ForResult

-0.26

@qq

-0.24

SCR

-0.24

åĨľå®¶

-0.24

æ½ĩ

-0.24

 undercover

-0.24

 predicts

-0.24

å®ŀçĶ¨

-0.23

 pivotal

-0.23

indx

-0.23

POSITIVE LOGITS

entes

0.27

rms

0.26

inherits

0.26

æ´»çĿĢ

0.25

Living

0.25

HEMA

0.25

omas

0.24

 Living

0.24

 stems

0.24

omen

0.24

Activations Density 0.195%

*

No Comments

No Known Activations