© 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. 47660
    Prev
    Next
    INDEX
    Explanations

    encoding data structures

    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
    белÑĮ
    -0.07
    ç£ĭ
    -0.07
    ç¼Ń
    -0.06
    Files
    -0.06
    lei
    -0.06
    já
    -0.06
    ueur
    -0.06
     Pictures
    -0.06
    åij¨æĺŁ
    -0.06
    åıĤä¸İè¯Ħ论
    -0.06
    POSITIVE LOGITS
    å¥īè¡Į
    0.07
    ä¼ł
    0.07
    pany
    0.07
    iche
    0.07
    ελ
    0.07
    opan
    0.07
    IPP
    0.07
     ke
    0.07
    arden
    0.06
    åıįéĿ¢
    0.06
    Activations Density 0.037%

    No Known Activations