© 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. 45314
    Prev
    Next
    INDEX
    Explanations

    purpose or function of

    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
    æĿĨèıĮ
    -0.08
    amba
    -0.08
    lands
    -0.07
     andata
    -0.07
    wic
    -0.07
    _HIDDEN
    -0.07
    à¸Ĺà¹Į
    -0.07
    øn
    -0.07
    对äºİä¸ĢäºĽ
    -0.07
    ening
    -0.07
    POSITIVE LOGITS
    gether
    0.09
    ä½ķå¤Ħ
    0.09
    åķĨä¸ļçĶ¨éĢĶ
    0.09
    ä½ķæĸ¹
    0.08
    /of
    0.08
    bidden
    0.08
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.08
    ä»Ģä¹Īåij¢
    0.08
    çļĦå°±æĺ¯
    0.08
    两个æĸ¹éĿ¢
    0.08
    Activations Density 0.003%

    No Known Activations