© 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. 32889
    Prev
    Next
    INDEX
    Explanations

    amount and information

    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
    ضا
    -0.08
    ÑĢим
    -0.07
    à¸ķà¹Īà¸Ńà¹Ħà¸Ľ
    -0.07
     conv
    -0.07
    ihen
    -0.07
    conv
    -0.06
    æ¦ķ
    -0.06
     Mora
    -0.06
    ¨
    -0.06
    onest
    -0.06
    POSITIVE LOGITS
    aida
    0.08
    æľīæĦı
    0.07
     exagger
    0.07
    धà¥Ģ
    0.07
    .abs
    0.07
    (fabs
    0.07
    ç¿Ķ
    0.07
     wre
    0.07
    æ·µ
    0.07
     Companion
    0.07
    Activations Density 0.011%

    No Known Activations