INDEX

Explanations

by

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

umps

-0.28

ouden

-0.27

ç¥¨

-0.27

 sensed

-0.26

åı¯æĥ³

-0.25

icycle

-0.25

 unavoid

-0.24

incible

-0.24

\brief

-0.24

çªģå¦Ĥ

-0.24

POSITIVE LOGITS

Refer

0.32

 refer

0.31

refer

0.31

çľĭä¸Ģä¸ĭ

0.31

åıĤèĢĥ

0.30

 please

0.29

 Refer

0.29

åıĥèĢĥ

0.29

éĺħè¯»

0.29

Ð·Ð½Ð°ÐºÐ¾Ð¼

0.29

Activations Density 0.006%

by

No Comments

No Known Activations