© 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. 3228
    Prev
    Next
    INDEX
    Explanations

    abstract concepts or negative states

    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
    дÑĢÑı
    -0.08
    å®ŀåľ¨å¤ª
    -0.07
    éĥijéĩį声æĺİ
    -0.07
    à¹ģà¸¥à¸°à¸ľà¸¹à¹ī
    -0.07
    注æĺİçļĦ
    -0.07
    ë§ģ
    -0.07
     ÙĪÙħا
    -0.07
    aday
    -0.07
    imenta
    -0.07
    .freeze
    -0.07
    POSITIVE LOGITS
    åı¯è¨Ģ
    0.07
    erset
    0.07
    ä¸Ģè¯į
    0.07
    äºĮåŃĹ
    0.07
    ism
    0.07
     lack
    0.07
     loss
    0.07
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    0.06
    åį³ä½į
    0.06
    å°±åľ°
    0.06
    Activations Density 0.369%

    No Known Activations