INDEX

Explanations

and

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

opl

-0.26

fet

-0.25

-abortion

-0.25

éĢģåİ»

-0.25

endon

-0.24

æķĿ

-0.24

fred

-0.24

orce

-0.24

bez

-0.23

rone

-0.23

POSITIVE LOGITS

æĲģ

0.27

ä¸»æīĵ

0.26

/li

0.25

 Sandwich

0.24

bah

0.24

 Reverse

0.23

lya

0.23

æİ¨èįĲ

0.23

çı²

0.23

ypy

0.23

Activations Density 0.026%

and

No Comments

No Known Activations