© 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. 18895
    Prev
    Next
    INDEX
    Explanations

    definitive conclusion or answer

    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
    ĵĴ
    -0.09
    ç«ĻåĨħæIJľç´¢
    -0.08
    注æĦıçļĦæĺ¯
    -0.08
    ekk
    -0.08
    ocab
    -0.08
    ä¹Łè¦ģ注æĦı
    -0.08
    Ģ
    -0.08
    åı¦å¤ĸè¿ĺæľī
    -0.08
    çĶļèĩ³è¿ĺæľī
    -0.07
    -dismiss
    -0.07
    POSITIVE LOGITS
     unequiv
    0.10
    综åIJĪ
    0.09
    综
    0.08
    æľ¬è´¨ä¸Ĭ
    0.08
    ç·ıåIJĪ
    0.08
    综ä¸ĬæīĢè¿°
    0.08
     definit
    0.08
    綾åIJĪ
    0.08
    æĢ»ä½ĵä¸Ĭ
    0.08
    æĢ»ä½ĵèĢĮè¨Ģ
    0.08
    Activations Density 0.010%

    No Known Activations