© 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. 18974
    Prev
    Next
    INDEX
    Explanations

    languages

    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
    æł¼å°Ķ
    -0.08
    æĶ¶èĹıæľ¬ç«Ļ
    -0.07
    .Broadcast
    -0.07
    åŀĭãģ®
    -0.07
    è½¼
    -0.07
    eneral
    -0.07
    åīįåIJİ
    -0.07
    amente
    -0.07
    orent
    -0.07
     jewish
    -0.07
    POSITIVE LOGITS
     languages
    0.10
     lingua
    0.10
     language
    0.10
     bahasa
    0.10
    æ±īè¯Ń
    0.09
    è¯Ńè¨Ģ
    0.09
     jÄĻzy
    0.09
     langue
    0.09
    ä¸Ńæĸĩ
    0.09
    Languages
    0.09
    Activations Density 0.138%

    No Known Activations