© 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. 63710
    Prev
    Next
    INDEX
    Explanations

    books and titles including colons

    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
     ÐijеÑĢе
    -0.07
    æ±°
    -0.07
    ç¨ĭ度ä¸Ĭ
    -0.07
     Completo
    -0.07
    siasi
    -0.07
    æ¨ĭ
    -0.07
    åĽłä¸ºåıªæľī
    -0.07
    hetto
    -0.07
    å¾¹
    -0.07
    Ñģей
    -0.07
    POSITIVE LOGITS
    !:
    0.08
     czyli
    0.07
    èĢĺ
    0.06
    åĨ
    0.06
    +:
    0.06
    é¦
    0.06
    è°ģæĿ¥
    0.06
    ?:
    0.06
     princ
    0.06
    رس
    0.06
    Activations Density 0.304%

    No Known Activations