© 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. 23858
    Prev
    Next
    INDEX
    Explanations

    numbers and names

    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
    rada
    -0.08
    oga
    -0.08
     Metropol
    -0.07
    çī¹å·¥
    -0.07
    rige
    -0.07
    imar
    -0.07
    _reserve
    -0.06
    decoder
    -0.06
     Rocha
    -0.06
    CPP
    -0.06
    POSITIVE LOGITS
    èݫ大çļĦ
    0.07
    sm
    0.07
    绪
    0.07
    表çİ°äºĨ
    0.07
    ä¸įèµ·æĿ¥
    0.07
    帼
    0.07
     Significant
    0.06
    viet
    0.06
    /feed
    0.06
    гоÑĢе
    0.06
    Activations Density 0.203%

    No Known Activations