INDEX

Explanations

I

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä½Ī

-0.28

obs

-0.27

 Hour

-0.26

æ¸Ĭ

-0.26

æµĨ

-0.25

æĭŁ

-0.25

 spir

-0.25

cia

-0.24

imit

-0.24

ä½ĵè´¨

-0.24

POSITIVE LOGITS

çĩĬ

0.28

 Marino

0.27

å¥ļ

0.27

 PÃºblico

0.26

è°Ľ

0.26

aku

0.26

edic

0.25

åĪĨéĴŁå·¦åı³

0.24

Ð°ÑĢÐ°

0.24

 betr

0.23

Activations Density 0.005%

I

No Comments

No Known Activations