© 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. 16433
    Prev
    Next
    INDEX
    Explanations

    URLs with tech/developer domains

    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
     whopping
    -0.08
    .gmail
    -0.07
    juÄį
    -0.07
    订éĺħä¸ĵæłı
    -0.06
    ä¿¡æģ¯ä¸¾æĬ¥
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    íķĻíļĮ
    -0.06
    .shtml
    -0.06
    åħ¶ä½Ļ
    -0.06
    åķĨä¸ļçī¹è®¸ç»ıèIJ¥
    -0.06
    POSITIVE LOGITS
    æŁ¥æŁ¥
    0.09
    å¼Ģå±ķ好
    0.07
    ä½ľåĵģåĨħ容
    0.07
    ç«Ļç«Ļ
    0.07
    ä¸Ģèµ·åŃ¦ä¹ł
    0.07
    itest
    0.07
    .me
    0.07
    æĢ»ç»ĵä¸Ģä¸ĭ
    0.07
    -icons
    0.06
    å¼Ģ个
    0.06
    Activations Density 0.351%

    No Known Activations