© 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. 24074
    Prev
    Next
    INDEX
    Explanations

    classification of things

    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
    è£Ķ
    -0.08
    wards
    -0.08
    acles
    -0.08
    à¹Ģà¸Ľà¸¥à¹Īา
    -0.08
    à¸ı
    -0.08
    iley
    -0.07
    leigh
    -0.07
    sworth
    -0.07
    INESS
    -0.07
    iness
    -0.07
    POSITIVE LOGITS
     ulang
    0.11
    /class
    0.08
    åĻ¨çŃī
    0.08
    åĻ¨çļĦ
    0.08
    /design
    0.08
    à¹Ħวà¹īà¹ĥà¸Ļ
    0.08
    zione
    0.08
    åĻ¨
    0.07
    asikan
    0.07
    zá
    0.07
    Activations Density 0.025%

    No Known Activations