© 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. 9863
    Prev
    Next
    INDEX
    Explanations

    names of people and institutions

    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
    elp
    -0.09
    รวà¸ĩ
    -0.08
    ä¸Ģç¯ĩ
    -0.08
     maupun
    -0.07
    ByName
    -0.07
    ingan
    -0.07
    रण
    -0.07
    qli
    -0.07
    åı¯èĥ½çļĦ
    -0.07
    ä¼ĺç§Ģå¥ĸ
    -0.07
    POSITIVE LOGITS
    olat
    0.07
    aeda
    0.07
    agna
    0.07
     eter
    0.07
     series
    0.07
    ç³»åĪĹ
    0.06
    ä½ĵç³»
    0.06
    enstein
    0.06
    ä½ĵç³»ä¸Ń
    0.06
    kler
    0.06
    Activations Density 0.231%

    No Known Activations