INDEX

Explanations

Agency

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

FINE

-0.35

aeda

-0.30

 Descriptor

-0.28

DataTask

-0.27

otre

-0.26

ulen

-0.26

akis

-0.25

åĪ¶åº¦æĶ¹éĿ©

-0.25

 surg

-0.25

insky

-0.25

POSITIVE LOGITS

ìĸ¸

0.28

ä¼ģä¸ļæıĲä¾Ľ

0.26

-prop

0.25

(private

0.24

-param

0.24

åºĦåĽŃ

0.24

hit

0.24

Tow

0.24

çŃĭ

0.24

è¿Ľåıĸ

0.23

Activations Density 0.008%

Agency

No Comments

No Known Activations