© 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. 45153
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    Ł
    -0.07
    äºijé¾Ļ
    -0.06
    è¯Ń
    -0.06
    isting
    -0.06
    oard
    -0.06
     pros
    -0.06
    idamente
    -0.06
    à¸Ĺร
    -0.06
    aning
    -0.06
    uku
    -0.06
    POSITIVE LOGITS
    å¸Ĥ人æ°ijæ³ķéĻ¢
    0.08
    _dummy
    0.08
     Steck
    0.07
    _PRIMARY
    0.07
    éĢĨè¡Į
    0.07
    åĴĮä¸ĸçķĮ
    0.07
    èĬĻ
    0.07
    ourn
    0.07
    agia
    0.07
    ichel
    0.07
    Activations Density 0.012%

    No Known Activations