© 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. 7901
    Prev
    Next
    INDEX
    Explanations

    Minister 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
    å¸Ĥ人大常å§Ķä¼ļ
    -0.08
    åݿ人æ°ijæ³ķéĻ¢
    -0.08
    owntown
    -0.08
    åħ¬åı¸èij£äºĭéķ¿
    -0.08
    å¸Ĥå§Ķç»Ħç»ĩéĥ¨
    -0.08
    ontre
    -0.08
    å¸Ĥå§Ķ书记
    -0.08
    åĮºå§Ķ书记
    -0.08
    å¸ĤæĶ¿åįı
    -0.07
    å¸Ĥå§Ķå¸ĤæĶ¿åºľ
    -0.07
    POSITIVE LOGITS
    åĨħéĺģ
    0.09
     cabinet
    0.08
    åŃľ
    0.08
    endela
    0.08
     Cabinet
    0.07
     ministries
    0.07
     ìŀ¥ê´Ģ
    0.07
    大èĩ£
    0.07
    паÑĢ
    0.07
    ä¸ĢæĦı
    0.07
    Activations Density 0.214%

    No Known Activations