© 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. 4414
    Prev
    Next
    INDEX
    Explanations

    comparisons and programming 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
    ikel
    -0.08
     hopefully
    -0.07
     ê¹
    -0.07
     appunto
    -0.07
    hek
    -0.07
    并ä¸Ķè¿ĺ
    -0.06
    ety
    -0.06
    uner
    -0.06
    omen
    -0.06
    teg
    -0.06
    POSITIVE LOGITS
     ÑĤоже
    0.10
    ä¹Łæľīåı¯èĥ½
    0.09
    æīįæĺ¯
    0.09
    æĽ´ç¬¦åIJĪ
    0.09
    ä¹Łä¸įéĶĻ
    0.08
    ä¹Łåı¯èĥ½æĺ¯
    0.08
    éĤ£ä¹Łæĺ¯
    0.08
    æīįæĺ¯æľĢ
    0.08
    åı¸
    0.08
    ä¹Łæĺ¯ä¸ª
    0.08
    Activations Density 0.038%

    No Known Activations