© 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. 40468
    Prev
    Next
    INDEX
    Explanations

    molecular targeted therapy

    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
    ä¸įé½IJ
    -0.09
    ä¸įåīį
    -0.08
    بÙĪب
    -0.08
    WithData
    -0.08
    ä¸įè¾ŀ
    -0.07
    аем
    -0.07
    angkap
    -0.07
    OutOfBounds
    -0.07
    LOPT
    -0.07
    æļ§
    -0.07
    POSITIVE LOGITS
    é¾Ħ
    0.07
     version
    0.07
     Version
    0.07
    çīĪ
    0.07
    ische
    0.07
    ity
    0.07
    inite
    0.06
    adem
    0.06
    )$_
    0.06
    æĪijçľĭçĿĢ
    0.06
    Activations Density 0.001%

    No Known Activations