© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26468
    Prev
    Next
    INDEX
    Explanations

    provide goods, services, or education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tersendiri
    -0.08
    åºĶ该注æĦı
    -0.08
    éľĢè¦ģ注æĦı
    -0.08
    izzer
    -0.08
    ollo
    -0.08
    çĿĢèĩªå·±çļĦ
    -0.08
    à¸Ķà¸Ńà¸Ļ
    -0.08
    åĢ¼å¾Ĺä¸ĢæıIJ
    -0.08
    大大æıIJé«ĺäºĨ
    -0.08
     suce
    -0.08
    POSITIVE LOGITS
     möglichst
    0.16
    å°½åı¯èĥ½
    0.15
    å°½åı¯èĥ½çļĦ
    0.12
    ä¸ºçĽ®çļĦ
    0.11
    å°½åı¯èĥ½åľ°
    0.10
    æľĢ大éĻIJåº¦åľ°
    0.10
    èĢĮéĿŀ
    0.10
     ×ķ׾×Ķ
    0.10
    à¹ĥหà¹īà¹Ħà¸Ķà¹ī
    0.10
    并确ä¿Ŀ
    0.09
    Activations Density 0.482%

    No Known Activations