© 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. 25108
    Prev
    Next
    INDEX
    Explanations

    because, since, due to

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Santiago
    -0.08
    è¿Ļç§įè¡Į为
    -0.08
    ×ľ×ª
    -0.07
    pras
    -0.07
    VRT
    -0.07
    IFn
    -0.06
    以åıĬä¸İ
    -0.06
    .tk
    -0.06
    ystal
    -0.06
    ulary
    -0.06
    POSITIVE LOGITS
    è¦ģè·Ł
    0.08
    è¦ģåĴĮ
    0.08
    æīĢ以æīį
    0.07
    è¦ģä¸İ
    0.07
    hall
    0.07
    ä¸įçĦ¶
    0.07
    erschutz
    0.06
     otherwise
    0.06
    è¦ģä¸įçĦ¶
    0.06
    åºŁè¯Ŀ
    0.06
    Activations Density 0.037%

    No Known Activations