© 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. 56535
    Prev
    Next
    INDEX
    Explanations

    smallest and first

    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
    _factory
    -0.08
    ifar
    -0.08
    ä¸įäºī
    -0.08
    err
    -0.07
    æĢ»ç»ĵåĴĮ
    -0.07
    å¿Ĺæĺİ
    -0.07
    à¸Łà¸£à¸µ
    -0.07
    .createObject
    -0.07
     Mane
    -0.07
    oram
    -0.07
    POSITIVE LOGITS
    -ever
    0.10
     tiên
    0.09
    kest
    0.08
     acceptable
    0.07
    ä¹Łæĺ¯æľĢ
    0.07
    ENTION
    0.07
    lijk
    0.07
     ever
    0.07
    çĥĪ
    0.07
    imum
    0.07
    Activations Density 0.007%

    No Known Activations