© 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. 46878
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    <|box_end|>
    -0.08
    abora
    -0.08
    çľĭèµ·æĿ¥å¾Ī
    -0.07
    ีà¹Īย
    -0.07
    âĢ¦)
    -0.07
    eles
    -0.07
    hing
    -0.07
     freaking
    -0.07
    ÑģÑĤен
    -0.07
     sedu
    -0.07
    POSITIVE LOGITS
    nu
    0.07
    .googlecode
    0.07
    为满足
    0.06
    çļĦç¼ĺæķħ
    0.06
    iculum
    0.06
    èĻ½
    0.06
    åij¨å²ģ以ä¸Ĭ
    0.06
    am
    0.06
    om
    0.06
    为éģ¿åħį
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.