© 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. 47136
    Prev
    Next
    INDEX
    Explanations

    abilities and strengths

    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
    פ×ķ
    -0.07
     betr
    -0.07
    epoch
    -0.07
    éĶĻ综
    -0.07
    纲
    -0.07
    _epoch
    -0.06
     weighing
    -0.06
    æİĴæĶ¾æłĩåĩĨ
    -0.06
    è¿ĩå¢ĥ
    -0.06
    èIJ½èIJ½
    -0.06
    POSITIVE LOGITS
    ä¸ĵéķ¿
    0.16
    æĵħéķ¿çļĦ
    0.15
    çī¹éķ¿
    0.15
     talents
    0.13
    ä¸ĵç²¾
    0.13
     talent
    0.13
    ä¸ĵä¸ļæĬĢèĥ½
    0.12
     specialization
    0.11
    天èµĭ
    0.11
    æĬĢèĥ½
    0.11
    Activations Density 0.221%

    No Known Activations