© 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. 50890
    Prev
    Next
    INDEX
    Explanations

    comments and documentation

    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
    éĤ£æł·
    -0.07
    æľīåĬł
    -0.07
     att
    -0.07
    çĥŃéŨæĸĩç«ł
    -0.07
    æ°¸ä¹ħæĢ§
    -0.06
    ä¸į计
    -0.06
    ãģ¨ãģĦãģĨãģĭ
    -0.06
    ä¸įä½Ĩ
    -0.06
     additionally
    -0.06
    解æĶ¾æĢĿæĥ³
    -0.06
    POSITIVE LOGITS
    {@
    0.08
    ï¼Ĭï¼Ĭ
    0.07
    åĿĬ
    0.07
    estan
    0.07
     './
    0.07
    åŁł
    0.07
     '_
    0.07
     onDataChange
    0.07
    č
    0.07
    æīĢ欲
    0.07
    Activations Density 0.005%

    No Known Activations