© 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. 45170
    Prev
    Next
    INDEX
    Explanations

    font awesome, sysIP, COM_POST

    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
    uera
    -0.07
    onie
    -0.07
    adden
    -0.07
    on
    -0.07
    acci
    -0.06
    ukai
    -0.06
    tain
    -0.06
    .Base
    -0.06
    éł
    -0.06
    ombe
    -0.06
    POSITIVE LOGITS
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.08
    éĥijéĩį声æĺİ
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    æľ¬å¸ĸ
    0.08
    ALLOC
    0.08
    ills
    0.07
    ä¸Ģ度çļĦ
    0.07
    IALIZED
    0.07
    imately
    0.07
    egen
    0.07
    Activations Density 0.006%

    No Known Activations