© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37759
    Prev
    Next
    INDEX
    Explanations

    groups and members

    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
    ilien
    -0.07
    dain
    -0.07
    APPED
    -0.07
    ENCIAS
    -0.07
    zog
    -0.07
    kais
    -0.07
    çļĦä¸ĢçĶŁ
    -0.07
    ä¸īåĨľ
    -0.07
    /extensions
    -0.07
    ãģĮåħ¥
    -0.07
    POSITIVE LOGITS
    æĪIJåijĺ
    0.12
     members
    0.11
    _members
    0.11
    çļĦæĪIJåijĺ
    0.10
    ä¸ŃçļĦæīĢæľī
    0.10
     Members
    0.10
     consisting
    0.10
    æĪIJåĵ¡
    0.10
    æĪIJåijĺçļĦ
    0.09
    çļĦä¸Ģåijĺ
    0.09
    Activations Density 0.290%

    No Known Activations