© 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. 13055
    Prev
    Next
    INDEX
    Explanations

    function definitions

    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
    çĽ¸ä¿¡åľ¨
    -0.07
    ä¸įèĥľ
    -0.07
    éģĵåıĭ
    -0.07
    è¯¥æľº
    -0.07
    Ñħла
    -0.07
    resp
    -0.07
    åݲ
    -0.07
    غد
    -0.07
    élite
    -0.07
    zeuge
    -0.07
    POSITIVE LOGITS
    å°Ĩè¿ĻäºĽ
    0.10
    对ä¸Ĭè¿°
    0.10
    æĬĬè¿ĻäºĽ
    0.10
     combining
    0.10
    综åIJĪ
    0.09
     combine
    0.09
    .combine
    0.09
    Combine
    0.09
    è¿Ŀåıįä¸Ĭè¿°
    0.09
    ç»Ħè£ħ
    0.09
    Activations Density 0.064%

    No Known Activations