© 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. 41378
    Prev
    Next
    INDEX
    Explanations

    divisibility or receptors

    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
    ouve
    -0.07
    ree
    -0.07
    rene
    -0.07
    inho
    -0.07
    inata
    -0.07
    imuth
    -0.07
     duplex
    -0.07
    è¿İéļ¾
    -0.07
    Grab
    -0.06
    ä½łåij¢
    -0.06
    POSITIVE LOGITS
    åĩłäºº
    0.09
    社ä¼ļåĮĸ
    0.08
    .Runtime
    0.07
    è¿IJ
    0.07
    åĩłä¸ªäºº
    0.07
    åĽĽä¸Ń
    0.07
    æ°¸è¿ľçļĦ
    0.07
    åĩłçĤ¹
    0.07
    奴
    0.07
    æĺĤ
    0.06
    Activations Density 0.002%

    No Known Activations