© 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. 50621
    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
    oons
    -0.07
    loy
    -0.07
    èµ°é«ĺ
    -0.07
    اÙĨ
    -0.07
    \Bundle
    -0.07
    รุ
    -0.07
     Colomb
    -0.06
     Pue
    -0.06
    tsky
    -0.06
    rench
    -0.06
    POSITIVE LOGITS
    ä¸ĢæĭĽ
    0.08
    åѵ
    0.07
    _gid
    0.07
    vär
    0.07
    Õ¤
    0.07
    ÑĩеÑģ
    0.07
    case
    0.07
    ighted
    0.07
    èıľåĪĢ
    0.07
    ائب
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.