INDEX

Explanations

no

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EMU

-0.29

adol

-0.28

plements

-0.26

inel

-0.26

 kadar

-0.25

 infix

-0.25

 crash

-0.25

entials

-0.25

UEL

-0.25

èĶļ

-0.24

POSITIVE LOGITS

thur

0.28

æ½Ń

0.25

ACP

0.25

dde

0.25

dba

0.24

 Tomas

0.24

æµģåħ¥

0.24

 stuffing

0.24

åİ®

0.24

åĽ¤

0.24

Activations Density 0.004%

no

No Comments

No Known Activations