INDEX

Explanations

in

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

Si

-0.28

ees

-0.28

 girls

-0.28

dl

-0.27

YS

-0.26

Si

-0.26

_si

-0.25

é½¡

-0.25

éĻ¤

-0.25

dc

-0.25

POSITIVE LOGITS

busters

0.27

è½®

0.27

 titre

0.25

agra

0.24

adera

0.24

ivery

0.24

iena

0.24

 Scotia

0.23

ertest

0.23

Traditional

0.23

Activations Density 0.005%

in

No Comments

No Known Activations