© 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. 20255
    Prev
    Next
    INDEX
    Explanations

    stem cells, disorders

    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
    æĬ¥åijĬåİħ
    -0.07
     Hiến
    -0.07
    æ¯ķä¸ļåħ¸ç¤¼
    -0.07
     αÏĥÏĨα
    -0.07
    hashed
    -0.07
    ndl
    -0.07
    awat
    -0.07
    imately
    -0.07
    inski
    -0.07
    olia
    -0.07
    POSITIVE LOGITS
     Walters
    0.07
    æł¸
    0.06
    å¸Į
    0.06
    èĩŃ
    0.06
    arend
    0.06
    é
    0.06
    ë¥
    0.06
    è²Į
    0.06
     Co
    0.06
    ées
    0.06
    Activations Density 1.560%

    No Known Activations