© 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. 63336
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    mage
    -0.07
    .bin
    -0.07
    mega
    -0.07
     comp
    -0.07
     bin
    -0.07
    pje
    -0.07
    湿润
    -0.07
    enje
    -0.06
    cient
    -0.06
    _AREA
    -0.06
    POSITIVE LOGITS
    ikel
    0.08
    lessness
    0.07
    §
    0.07
    ä¸įä¸Ĭ
    0.07
    acha
    0.07
    ambu
    0.07
    ugu
    0.07
    auge
    0.07
    æľ¬ç½ijç«Ļ
    0.07
    hov
    0.07
    Activations Density 0.000%

    No Known Activations