© 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. 32774
    Prev
    Next
    INDEX
    Explanations

    copyright licenses / links

    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
    raries
    -0.11
    maÃŁen
    -0.10
    zelfde
    -0.10
    ly
    -0.10
    à¥į
    -0.09
    Ùĩ
    -0.09
    à¥įह
    -0.09
    ãĤĪãģĨãģª
    -0.08
    ой
    -0.08
    à¤ģ
    -0.08
    POSITIVE LOGITS
    ation
    0.10
    ////////////////////////////////////////////////////////////////
    0.09
    åĮªæµħ
    0.09
    itude
    0.08
    ÑİÑĤ
    0.08
    лайн
    0.08
    sWith
    0.08
    orary
    0.08
    ание
    0.08
    portun
    0.08
    Activations Density 0.214%

    No Known Activations