© 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. 26339
    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
    åįłæľī
    -0.07
    大åı¯
    -0.07
     ÐŁÐ¾ÐºÐ°Ð·Ð°
    -0.06
    ÑĩеÑĢ
    -0.06
     ::
    -0.06
    ofs
    -0.06
    å±±ä¸ĭ
    -0.06
    roud
    -0.06
    uge
    -0.06
    oda
    -0.06
    POSITIVE LOGITS
    ernos
    0.08
    kaar
    0.07
    endet
    0.07
    à®±à¯ģ
    0.07
    æĢ»èĢĮè¨Ģä¹ĭ
    0.07
    enskap
    0.07
    _CLI
    0.07
    ichtet
    0.07
    CIO
    0.07
    éricas
    0.07
    Activations Density 0.000%

    No Known Activations