INDEX

Explanations

Aff

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

æ³£

-0.26

IVED

-0.25

icated

-0.25

åı³ä¾§

-0.25

æļĹ

-0.25

rix

-0.24

 bisexual

-0.24

.assign

-0.24

åłĨ

-0.23

anos

-0.23

POSITIVE LOGITS

 Shapiro

0.26

ç©°

0.25

ç¬Ħ

0.25

ÙĥÙĨ

0.25

åľ¨äºİ

0.25

intage

0.24

ollections

0.24

 GmbH

0.24

.Configuration

0.23

emption

0.23

Activations Density 0.053%

Aff

No Comments

No Known Activations