© 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. 15673
    Prev
    Next
    INDEX
    Explanations

    FreeType project component

    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
    è´¨
    -0.07
    æĭĤ
    -0.06
    _fd
    -0.06
    ammo
    -0.06
    rowse
    -0.06
    æĹıèĩªæ²»å·ŀ
    -0.06
    ä¸įåĢĴ
    -0.06
    entai
    -0.06
    omin
    -0.06
    ary
    -0.06
    POSITIVE LOGITS
    缴æİ¥æĪĸ
    0.08
    Javascript
    0.08
    .Factory
    0.07
    atform
    0.07
    æļĤè¡Įè§Ħå®ļ
    0.07
    chette
    0.07
    posito
    0.07
    isable
    0.07
    æ²¹çĽIJ
    0.07
    Metro
    0.07
    Activations Density 0.003%

    No Known Activations