© 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. 63629
    Prev
    Next
    INDEX
    Explanations

    binding pockets and active sites

    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
    æĻ®åıĬ
    -0.08
    åŀ¢
    -0.07
     conscient
    -0.07
    erdo
    -0.07
    èĩªæĦĪ
    -0.07
     intest
    -0.07
     statistic
    -0.07
     gql
    -0.07
    好çľĭçļĦ
    -0.06
    erden
    -0.06
    POSITIVE LOGITS
     surrounding
    0.09
    ÏĨι
    0.08
    riminator
    0.08
     trợ
    0.08
    ÑģÑĤеÑĢ
    0.08
    æĺ¥éĽ¨
    0.07
     acidic
    0.07
    ster
    0.07
     workspace
    0.07
     accommodating
    0.07
    Activations Density 0.077%

    No Known Activations