© 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. 24687
    Prev
    Next
    INDEX
    Explanations

    as / sebagai / jako

    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
    _preview
    -0.07
    åIJĦè¡Į
    -0.07
    ilta
    -0.06
    èĥĮæĻ¯çļĦ
    -0.06
    æľī天
    -0.06
    ãģ¨ãģĵãĤįãģ§ãģĻ
    -0.06
    Ùħز
    -0.06
    æĪIJé¾Ļ
    -0.06
     atte
    -0.06
    elper
    -0.06
    POSITIVE LOGITS
    ä½ľä¸º
    0.17
    åı¯ä»¥ä½ľä¸º
    0.16
    åı¯ä½ľä¸º
    0.16
    åģļ为
    0.16
    ä¸įèĥ½ä½ľä¸º
    0.15
    ä½ľçĤº
    0.15
     jako
    0.14
    åģļçĤº
    0.14
    à¹Ģà¸Ľà¹ĩà¸Ļà¸ķัว
    0.14
     sebagai
    0.13
    Activations Density 0.866%

    No Known Activations