© 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. 7575
    Prev
    Next
    INDEX
    Explanations

    AM time

    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
    å·¥ç¨ĭçŃī
    -0.08
    çľĭåĪ°æĪij
    -0.08
    raje
    -0.07
    æľĢ大åĬŁçİĩ
    -0.07
    -spinner
    -0.07
     Saud
    -0.07
    prac
    -0.07
     perdana
    -0.07
    undles
    -0.07
    prat
    -0.07
    POSITIVE LOGITS
    heber
    0.07
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    0.07
    å¤ľæ·±
    0.07
    åIJĮæł·æĺ¯
    0.07
     Nur
    0.06
    å¥Ħ
    0.06
    çľ¼çľĭ
    0.06
     schl
    0.06
    åIJĮæł·çļĦ
    0.06
    OLL
    0.06
    Activations Density 0.351%

    No Known Activations