© 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. 13617
    Prev
    Next
    INDEX
    Explanations

    correlation functions

    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
    _errno
    -0.07
    åľ¨çİ©
    -0.07
    /apt
    -0.07
    /misc
    -0.07
    Rejected
    -0.07
    upati
    -0.07
    imers
    -0.07
     alternatives
    -0.06
    å¤ĸåĮħ
    -0.06
    çİ©åĦ¿
    -0.06
    POSITIVE LOGITS
    leta
    0.09
     correl
    0.09
    æľīæīĢæĢĿ
    0.08
    éļıæľº
    0.08
     dialogs
    0.07
     Operator
    0.07
    èĬ·
    0.07
    antin
    0.07
    æ¿ĢåıijåѦçĶŁ
    0.07
     Events
    0.07
    Activations Density 0.004%

    No Known Activations