INDEX

Explanations

of

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ought

-0.28

startup

-0.28

ä¸Ī

-0.27

ìĺ¬

-0.27

oodoo

-0.24

éĺ³

-0.24

è£Ļ

-0.23

 invest

-0.23

zung

-0.23

udson

-0.23

POSITIVE LOGITS

.EventType

0.26

abin

0.24

uja

0.23

å¥½åĲĥ

0.23

 tertiary

0.23

è¹

0.23

æĹ¶ç©º

0.23

isers

0.23

#ifndef

0.23

Ap

0.23

Activations Density 0.000%

of

No Comments

No Known Activations