© 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. 41956
    Prev
    Next
    INDEX
    Explanations

    word starts or follows specific prefixes

    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
    eggi
    -0.08
    cription
    -0.08
    ä¸ĭåIJĮ
    -0.08
    ÛĮدا
    -0.08
    ummies
    -0.07
    erture
    -0.07
     Höh
    -0.07
    varo
    -0.07
    Ïīμα
    -0.07
    _variable
    -0.07
    POSITIVE LOGITS
    ston
    0.07
    ä¿Ŀå§Ĩ
    0.06
    çľ·
    0.06
    luan
    0.06
     solamente
    0.06
    .best
    0.06
    å«Ĥ
    0.06
    kek
    0.06
     Duo
    0.06
    ”
    0.06
    Activations Density 0.009%

    No Known Activations