© 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. 56972
    Prev
    Next
    INDEX
    Explanations

    pKa, pI, Ca, Ki, Kd, constants

    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
    人éĥ½
    -0.08
    soever
    -0.07
    earch
    -0.07
    åı¯åĸľ
    -0.07
    uce
    -0.07
     ($.
    -0.06
    çĶŁæľº
    -0.06
    ×ķ׼׾
    -0.06
    akwa
    -0.06
    zat
    -0.06
    POSITIVE LOGITS
    appa
    0.08
    åĢ¼çļĦ
    0.07
    婦
    0.07
    ানা
    0.07
    秫
    0.07
    èİİæĭī
    0.07
    åĢ¤
    0.07
    urations
    0.07
    æĹ¥åł±
    0.07
    GBT
    0.07
    Activations Density 0.001%

    No Known Activations