© 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. 55275
    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
    adona
    -0.08
    entino
    -0.08
    ÉĻ
    -0.07
    isert
    -0.07
    /or
    -0.07
    ora
    -0.07
    ially
    -0.07
    es
    -0.07
    #ac
    -0.07
    åĪ°
    -0.07
    POSITIVE LOGITS
    нок
    0.07
    ëĭ´
    0.07
    -long
    0.07
    FINITE
    0.07
    folios
    0.06
    ivel
    0.06
    enment
    0.06
    nay
    0.06
    itude
    0.06
    人æĿ¥è¯´
    0.06
    Activations Density 0.000%

    No Known Activations