© 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. 44160
    Prev
    Next
    INDEX
    Explanations

    numbers and years

    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
    watan
    -0.07
    æĤ¨åı¯èĥ½
    -0.07
    DebugEnabled
    -0.07
    ialized
    -0.06
    w
    -0.06
    wil
    -0.06
    åı¯ä¸į
    -0.06
    汪
    -0.06
    åĩłä¸ªæĸ¹éĿ¢
    -0.06
    елÑĮ
    -0.06
    POSITIVE LOGITS
    umur
    0.08
    ró
    0.08
    nett
    0.07
    rong
    0.07
    ä¹Łå¥½
    0.07
    ä¸Ģ缴åĪ°
    0.07
    inki
    0.07
    ulasi
    0.07
    _requests
    0.07
     Ø´Ùĥ
    0.07
    Activations Density 0.221%

    No Known Activations