INDEX

Explanations

pulsed signals

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

Spr

-0.28

spr

-0.27

Spr

-0.27

CJK

-0.27

åīľ

-0.26

çļĦä¸ĢéĿ¢

-0.26

åĭº

-0.24

 rins

-0.24

ç¨İ

-0.24

 surpr

-0.23

POSITIVE LOGITS

icum

0.28

ä¸įå¼Ģ

0.27

æ¨¡

0.26

 reflective

0.26

 reflect

0.25

è¿ĺæĥ³

0.25

äº¤æĺĵä¸Ńå¿ĥ

0.25

 Magazine

0.24

ira

0.24

çļ®

0.24

Activations Density 0.005%

pulsed signals

No Comments

No Known Activations