© 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. 20050
    Prev
    Next
    INDEX
    Explanations

    webpage file extensions and database queries

    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
     Gug
    -0.08
    enha
    -0.07
    ebet
    -0.07
    essus
    -0.07
    endt
    -0.07
    æĹłæĦı
    -0.07
    istri
    -0.07
    /domain
    -0.07
     Jah
    -0.07
    dup
    -0.06
    POSITIVE LOGITS
    ydi
    0.07
    åĬ©æĶ»
    0.07
    гаÑĢ
    0.07
    .advance
    0.07
    koop
    0.06
     korona
    0.06
    åĬŁèĩ£
    0.06
    ìĸ¸
    0.06
    ampa
    0.06
    iek
    0.06
    Activations Density 0.564%

    No Known Activations