INDEX

Explanations

Various topics and sources

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å®Ī

-0.30

 rating

-0.28

 Toro

-0.27

oriented

-0.26

 conserv

-0.25

è¿Ļå¼ł

-0.25

 conven

-0.25

anging

-0.25

 standing

-0.24

 experiment

-0.24

POSITIVE LOGITS

egin

0.33

ÑģÑĤÐ°Ð²ÐºÐ°

0.26

\Abstract

0.25

à¸ĺà¸£

0.25

åŀĤçĽ´

0.25

 Approach

0.25

leri

0.23

æľīå®³

0.23

æĪĺçģ«

0.23

 forEach

0.23

Activations Density 0.134%

Various topics and sources

No Comments

No Known Activations