© 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. 14241
    Prev
    Next
    INDEX
    Explanations

    integration and connection

    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
    hafte
    -0.08
    ington
    -0.08
    hood
    -0.08
     индÑĥ
    -0.07
    à¸ĭà¹īำ
    -0.07
    ÙĪÙģØ©
    -0.07
    weisen
    -0.06
    åĺģ
    -0.06
    GenericType
    -0.06
    åĬĽè¡Į
    -0.06
    POSITIVE LOGITS
     seamlessly
    0.10
    /embed
    0.09
    åľ¨ä¸Ģèµ·çļĦ
    0.09
    asikan
    0.09
    è¿ĽæĿ¥çļĦ
    0.08
    uitive
    0.08
    åľ¨ä¸Ģèµ·
    0.08
     Bestandteil
    0.08
    度é«ĺ
    0.08
    à¹Ģà¸Ĥà¹īาà¸ģัà¸ļ
    0.08
    Activations Density 0.032%

    No Known Activations