INDEX

Explanations

Quotation marks

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

è¦ģä¹Ī

-0.29

iest

-0.25

chte

-0.25

è¦ģçĤ¹

-0.25

 bunch

-0.24

ipo

-0.24

ypical

-0.24

è¿ĺæĺ¯ä¼ļ

-0.24

em

-0.24

boa

-0.24

POSITIVE LOGITS

earing

0.28

icus

0.27

ears

0.25

egin

0.25

 Reyn

0.25

ecer

0.25

æĪĳä»¬éľĢè¦ģ

0.23

ä¸ŃåĽ½æĶ¿åºľ

0.23

ICATION

0.23

inas

0.23

Activations Density 0.003%

Quotation marks

No Comments

No Known Activations