© 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. 32044
    Prev
    Next
    INDEX
    Explanations

    settings and environments

    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
    stin
    -0.08
    à¸ŀัà¸Ļà¸ĺุà¹Į
    -0.07
    ÑĢони
    -0.07
    è¿ĽåŁİ
    -0.07
     ê
    -0.07
    vestig
    -0.07
    owie
    -0.07
    owska
    -0.06
    aky
    -0.06
     omin
    -0.06
    POSITIVE LOGITS
    à¹ģวà¸Ķลà¹īà¸Ńม
    0.10
    ãģ§ãģ®
    0.10
     situations
    0.10
     waarin
    0.10
    ìĹIJìĦľìĿĺ
    0.10
     circumstances
    0.09
    ä½ķåľ°
    0.09
     environments
    0.09
     contexts
    0.09
    ä¸ŃæĿ¥
    0.08
    Activations Density 0.079%

    No Known Activations