© 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. 34865
    Prev
    Next
    INDEX
    Explanations

    directory paths like src/main/resources

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    ulette
    -0.07
    屿
    -0.07
    大大çļĦ
    -0.07
    initi
    -0.07
    快讯
    -0.07
    ÑĤÑĢеÑĤÑĮ
    -0.07
    plen
    -0.07
     Aval
    -0.07
    inite
    -0.07
    деле
    -0.07
    POSITIVE LOGITS
    .Win
    0.07
    ç§ģæľį
    0.07
    zb
    0.07
    eces
    0.07
    าว
    0.07
    ева
    0.07
    iaux
    0.06
    kau
    0.06
    BUM
    0.06
    ä¸įæģ¯
    0.06
    Activations Density 0.013%

    No Known Activations