© 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. 60352
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or percentages

    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
    à¸Ĺยà¹Į
    -0.07
    isons
    -0.07
    è®°èĢħäºĨ解åĪ°
    -0.07
    apus
    -0.07
    ç¥ĸå®Ĺ
    -0.07
    воÑĢоÑĤ
    -0.07
    zada
    -0.07
    ivr
    -0.07
    à¸Īà¸Ļà¹Į
    -0.07
    ÙĤ
    -0.07
    POSITIVE LOGITS
    igue
    0.08
    ë¡Ŀ
    0.07
     chấp
    0.07
    stead
    0.07
     "&#
    0.07
    nect
    0.06
    .carousel
    0.06
    ืà¸Ńà¸ļ
    0.06
    uckle
    0.06
    olino
    0.06
    Activations Density 0.024%

    No Known Activations