© 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. 31594
    Prev
    Next
    INDEX
    Explanations

    method headings

    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
    verg
    -0.08
    å·ŀåĮº
    -0.07
    ibro
    -0.07
    eping
    -0.07
     scram
    -0.07
    ä¿¡
    -0.07
    غÙħ
    -0.07
    å®ļçļĦ
    -0.07
     Walters
    -0.07
    lys
    -0.07
    POSITIVE LOGITS
    oes
    0.07
    åıĬåĪ©æģ¯
    0.07
    æĹ¥åIJij
    0.06
    æĮĿ
    0.06
    ä¸İ建议
    0.06
    adv
    0.06
    ãģŁãģŁ
    0.06
     Dorf
    0.06
     tran
    0.06
    rong
    0.06
    Activations Density 0.206%

    No Known Activations