© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50221
    Prev
    Next
    INDEX
    Explanations

    next term in sequence

    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
     maxim
    -0.07
     Maxim
    -0.07
    rawer
    -0.06
     minim
    -0.06
    å¹¿æ³ĽåºĶçĶ¨äºİ
    -0.06
     orth
    -0.06
    .offsetTop
    -0.06
    è·¯æ¼Ķ
    -0.06
    ¸
    -0.06
     ras
    -0.06
    POSITIVE LOGITS
    æĸ°ç½ij
    0.09
    skr
    0.08
     nett
    0.08
    echa
    0.08
    à¹Ģà¸Ľà¸£
    0.07
    оба
    0.07
    еÑģÑģи
    0.07
     commend
    0.07
    ä¸īéĥ¨æĽ²
    0.07
    оÑĩÑĮ
    0.07
    Activations Density 0.007%

    No Known Activations