© 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. 46178
    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
    çİĸ
    -0.07
    lje
    -0.06
    ç»ĪæĹ¥
    -0.06
    çľĭåľ¨çľ¼éĩĮ
    -0.06
    .nom
    -0.06
    agu
    -0.06
     Sej
    -0.06
     centrally
    -0.06
     tal
    -0.06
    å®Ŀå¡Ķ
    -0.06
    POSITIVE LOGITS
    0.08
    æ½ĩ
    0.07
    /../
    0.07
    éĥ½åģļ
    0.07
    icot
    0.07
    lässlich
    0.07
    AnimationFrame
    0.07
    lesias
    0.07
    aaS
    0.07
    ẻo
    0.07
    Activations Density 0.000%

    No Known Activations