© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22961
    Prev
    Next
    INDEX
    Explanations

    finite groups and sets

    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
    usen
    -0.09
    ä¸ĩéĩĮ
    -0.07
    ä¸Ģ个åŃ©åŃIJ
    -0.07
    erti
    -0.07
    cle
    -0.07
    aim
    -0.07
    çĮĽ
    -0.07
    าะ
    -0.07
    ifen
    -0.06
    rente
    -0.06
    POSITIVE LOGITS
    éĿ¢æĹł
    0.08
    kok
    0.07
    ADE
    0.07
    第ä¸Ģ大
    0.07
    ANTS
    0.07
    สà¸Ļิà¸Ĺ
    0.07
    -review
    0.07
    ürg
    0.07
    éĹŃ
    0.07
     íĮ
    0.06
    Activations Density 0.012%

    No Known Activations