© 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. 1734
    Prev
    Next
    INDEX
    Explanations

    future, success, dreams, states

    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
    å·´å·´
    -0.08
    enni
    -0.07
    ropa
    -0.07
    fram
    -0.07
    à¸ĺรรมà¸Ĭาà¸ķิà¹ģละ
    -0.07
    thon
    -0.06
     Marketable
    -0.06
    itor
    -0.06
    ìłģìĿ´ê³ł
    -0.06
    utam
    -0.06
    POSITIVE LOGITS
    ãģ¨ãģĦãģ£ãģŁ
    0.09
    ãģĿãģĹãģ¦
    0.08
     ê·¸ë¦¬ê³ł
    0.07
     sowie
    0.07
    ciare
    0.07
    lt
    0.07
    ussen
    0.07
    ucks
    0.07
    alf
    0.06
    æĺ¯éĿŀ
    0.06
    Activations Density 0.061%

    No Known Activations