INDEX

Explanations

report

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

Ä±rl

-0.27

åłĨæĶ¾

-0.27

rÃ¤

-0.25

rites

-0.25

ç«£

-0.25

ableObject

-0.24

DY

-0.23

rif

-0.23

BOSE

-0.23

æĢģ

-0.23

POSITIVE LOGITS

.GetAxis

0.30

ç¼¨

0.29

SystemService

0.26

Ã¼cken

0.25

ä¿¡éĺ³

0.25

æ·¡å®ļ

0.25

å¯ĮåĬĽ

0.24

 guessed

0.24

 lower

0.24

æºº

0.24

Activations Density 0.001%

report

No Comments

No Known Activations