© 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. 25499
    Prev
    Next
    INDEX
    Explanations

    question

    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
    翼翼
    -0.08
    èµĦæºIJç½ij
    -0.07
    æ´½
    -0.07
    emente
    -0.06
    尿裤
    -0.06
    æĹ©é¤IJåIJİ
    -0.06
     Grav
    -0.06
    úst
    -0.06
    失æĺİ
    -0.06
    æĪij们ä¼ļ尽快
    -0.06
    POSITIVE LOGITS
     ÐĿовоÑģи
    0.08
     ÐļÑĢаÑģи
    0.07
    rina
    0.07
     ÐĹве
    0.07
     золоÑĤи
    0.07
    asket
    0.07
    Accessor
    0.07
    боÑĢов
    0.07
     yyn
    0.07
     kräf
    0.07
    Activations Density 0.065%

    No Known Activations