© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51958
    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
     –
    -0.07
    lave
    -0.07
    رÙħ
    -0.06
     Shed
    -0.06
    ered
    -0.06
     ض
    -0.06
    arian
    -0.06
    Âł
    -0.06
     thereof
    -0.06
    usa
    -0.06
    POSITIVE LOGITS
    IST
    0.08
    uos
    0.08
    olin
    0.08
    istrator
    0.07
    "is
    0.07
    çļĦ主导
    0.07
    好æĸĩ
    0.07
    ิส
    0.07
     bev
    0.07
    serialized
    0.07
    Activations Density 0.000%

    No Known Activations