© 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. 18375
    Prev
    Next
    INDEX
    Explanations

    code examples or technical descriptions

    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
    ÑİÑĢа
    -0.07
    达产
    -0.07
    łĢ
    -0.07
    为èį£
    -0.07
     McKay
    -0.07
    ä¸īå°º
    -0.07
    иÑģка
    -0.07
     lév
    -0.07
    ëĿ½
    -0.07
    ãĤ¤ãĥĦ
    -0.07
    POSITIVE LOGITS
    æľĢ好æĺ¯
    0.07
    åĥıä½ł
    0.07
    à¸Ńรà¹Į
    0.07
    ctor
    0.06
    اتب
    0.06
    æīįåı¯ä»¥
    0.06
    å°ļåı¯
    0.06
    stÄĻp
    0.06
    æŃ£ç»ı
    0.06
    è¶Ĭ好
    0.06
    Activations Density 0.030%

    No Known Activations