© 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. 31070
    Prev
    Next
    INDEX
    Explanations

    row and column indices

    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
    apan
    -0.09
    ÏĦÏģÏĮ
    -0.07
    hora
    -0.07
    orphic
    -0.07
    ÏĥÏĦαÏĥη
    -0.07
    stants
    -0.07
    wod
    -0.07
     stron
    -0.07
    缸ç»ĵåIJĪçļĦæĸ¹å¼ı
    -0.07
    ignet
    -0.07
    POSITIVE LOGITS
    ucht
    0.07
    ç·Ĵ
    0.06
    çĥĪæĹ¥
    0.06
    天èĬ±æĿ¿
    0.06
    alda
    0.06
    æĽ
    0.06
    lint
    0.06
     tiên
    0.06
    åĸľéĹ»
    0.06
    bot
    0.06
    Activations Density 0.007%

    No Known Activations