© 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. 31660
    Prev
    Next
    INDEX
    Explanations

    . followed by a word

    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
    ä¹łæĥ¯
    -0.07
    ä¹łæĥ¯æĢ§
    -0.07
     seeming
    -0.07
    amento
    -0.06
    éĢļ常æĥħåĨµä¸ĭ
    -0.06
    à¦ļিত
    -0.06
    ä¸įæĺİ
    -0.06
     ordinarily
    -0.06
    åĹľ
    -0.06
    icolor
    -0.06
    POSITIVE LOGITS
     вов
    0.08
    MDB
    0.08
    cee
    0.08
    ãĤ¿ãĥ¼ãĤ²ãĥĥãĥĪ
    0.07
    éĤĢ
    0.07
     teÅŁ
    0.07
    è¿Ľè¡Įä¿®æĶ¹
    0.07
    ç²¾å¿ĥ设计
    0.07
    _loaded
    0.07
    æĶ¹ç¼ĸ
    0.07
    Activations Density 0.017%

    No Known Activations