© 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. 60492
    Prev
    Next
    INDEX
    Explanations

    Ka, Fs, E, aged, d

    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
    éĴ§
    -0.08
    /english
    -0.08
     candidature
    -0.07
    建åĨĽ
    -0.07
    ubles
    -0.07
    {/
    -0.07
    ffee
    -0.07
    ople
    -0.07
    hlas
    -0.07
    atel
    -0.07
    POSITIVE LOGITS
     ''
    0.08
    )):
    0.07
    çº
    0.07
    ãģªãģ®ãģ¯
    0.07
    à¸Ńà¸ģ
    0.07
     ped
    0.07
    iol
    0.06
    ault
    0.06
    ']):
    0.06
    çļĦå°±æĺ¯
    0.06
    Activations Density 0.047%

    No Known Activations