INDEX

Explanations

lean

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¸Ŀ

-0.30

æĹłåģ¿

-0.28

å´©

-0.27

di

-0.26

shl

-0.26

Di

-0.26

 Sant

-0.25

 táº¯t

-0.25

æĶ¹åıĺ

-0.25

MI

-0.24

POSITIVE LOGITS

è¿ĻæĹ¶åĢĻ

0.31

scenario

0.29

zing

0.26

è¿Ļä¸ªæĹ¶åĢĻ

0.25

ammers

0.25

arking

0.25

é«ĺå³°

0.25

leasing

0.24

æıª

0.24

áº¡ch

0.24

Activations Density 0.034%

lean

No Comments

No Known Activations