INDEX

Explanations

cord

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

 Radical

-0.28

åłĩ

-0.25

jian

-0.25

 Florian

-0.24

inned

-0.24

ç¿ĺ

-0.24

 Helpful

-0.23

.Annotations

-0.23

æĪĲå°±

-0.23

ungen

-0.23

POSITIVE LOGITS

ableView

0.27

ndl

0.27

apur

0.25

å¹Į

0.24

arry

0.24

å¤§æĪĺ

0.24

æµĨ

0.24

AsStream

0.24

ede

0.23

åįķè½¦

0.23

Activations Density 0.009%

cord

No Comments

No Known Activations