INDEX

Explanations

which

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

ials

-0.30

pliers

-0.26

ceiver

-0.26

xes

-0.26

 Third

-0.25

+S

-0.25

æŀ£

-0.25

å¹¸

-0.25

íľ´

-0.24

 Fourth

-0.24

POSITIVE LOGITS

jdbc

0.31

æĶ¹åıĺ

0.27

å¥½å¥½

0.25

è½½

0.25

ku

0.24

toc

0.24

CDC

0.24

èķ¨

0.24

 affecting

0.23

 forcefully

0.23

Activations Density 0.011%

which

No Comments

No Known Activations