INDEX

Explanations

Personal narratives/discussions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æİł

-0.29

 cond

-0.29

log

-0.27

Pra

-0.26

 conditioning

-0.26

cond

-0.26

pra

-0.26

conditional

-0.25

 body

-0.25

 conditioner

-0.25

POSITIVE LOGITS

hift

0.27

ç²¾ç¥ŀ

0.27

thren

0.27

 ((__

0.26

áĢī

0.26

avy

0.25

",__

0.25

à¸·à¸Ńà¸Ļ

0.25

"display

0.25

prep

0.24

Activations Density 0.570%

Personal narratives/discussions

No Comments

No Known Activations