© 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. 33551
    Prev
    Next
    INDEX
    Explanations

    AzPainter, HTML, Contributors, license

    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
    çľ¼çľĭçĿĢ
    -0.07
    Ùħز
    -0.07
    åĨ²åĬ¨
    -0.07
    æĴ¼
    -0.06
    à¹ģà¸ŀ
    -0.06
    éĺħè¯»æľ¬æĸĩ
    -0.06
    ëŀĺ
    -0.06
    æµ¦ä¸ľ
    -0.06
     getP
    -0.06
    èģĮä¸ļæĬĢæľ¯åѦéĻ¢
    -0.06
    POSITIVE LOGITS
    èģĮä¸ļåѦéĻ¢
    0.10
    è¡Įä¸ļåĬ¨æĢģ
    0.08
    å½ĵçĦ¶
    0.07
    ç¬¬åĽĽåŃ£
    0.07
    ainer
    0.07
    ambre
    0.07
    âĢķâĢķâĢķâĢķ
    0.07
     пÑĢоÑĤивоÑĢе
    0.07
    å¦Ĥæŀľæĺ¯
    0.07
    addle
    0.07
    Activations Density 1.726%

    No Known Activations