INDEX

Explanations

sm

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä»Ģä¹Ī

-0.27

è¿Ļä¸¤ç§į

-0.26

ard

-0.26

\|

-0.25

çĺŁ

-0.25

ARD

-0.24

å¹¿åĳĬæľįåĬ¡

-0.24

ensis

-0.24

Ø¹Ø¸Ùħ

-0.24

opath

-0.23

POSITIVE LOGITS

iore

0.29

Bri

0.27

ritt

0.27

å¥½äºº

0.26

odge

0.26

åª³å¦ĩ

0.25

nip

0.25

 tight

0.24

tight

0.24

morgan

0.24

Activations Density 0.001%

sm

No Comments

No Known Activations