© 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. 63361
    Prev
    Next
    INDEX
    Explanations

    tie breaking selection

    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§Ķæīĺ代çIJĨ人
    -0.08
    oppen
    -0.07
    大ç¥ŀ
    -0.07
    andia
    -0.07
    转åŀĭåıijå±ķ
    -0.07
    ä¸įçŁ¥æīĢ
    -0.07
    åĩĨç¡®æĢ§åĴĮåIJĪæ³ķæĢ§
    -0.07
    æīĢæĢĿ
    -0.07
    æĭĽå¾ħ
    -0.07
    olata
    -0.07
    POSITIVE LOGITS
    æľīç¦ı
    0.08
    ahl
    0.08
    ahi
    0.07
     ìļ°ìĦł
    0.07
     implementation
    0.07
    ä¸įåı¯éģ¿åħįçļĦ
    0.07
    ãģªãĤĭãģ¹ãģı
    0.07
    æľºä¼ļ
    0.07
    implementation
    0.07
     Implementation
    0.07
    Activations Density 0.004%

    No Known Activations