© 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. 49455
    Prev
    Next
    INDEX
    Explanations

    perpendicular to

    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
    Å¡a
    -0.08
    ÑģÑĤили
    -0.08
    åľ¨ç¤¾åĮº
    -0.08
    ozen
    -0.08
    eke
    -0.07
    spir
    -0.07
    ä»ĸå¿ĥéĩĮ
    -0.07
    شتÙĩ
    -0.07
    åľ¨åŃ¦ä¹łä¸Ĭ
    -0.07
    ç²¾ç¥ŀä¸ĬçļĦ
    -0.07
    POSITIVE LOGITS
    à¸ķั
    0.07
    vez
    0.07
    ved
    0.06
     incoming
    0.06
    é¢ģ
    0.06
    olato
    0.06
    天éķ¿
    0.06
    ruk
    0.06
    pip
    0.06
     acquis
    0.06
    Activations Density 0.030%

    No Known Activations