© 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. 37718
    Prev
    Next
    INDEX
    Explanations

    long int data types and operators

    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
    ä¸Ĭè¿°äºĭå®ŀ
    -0.08
    á»±
    -0.08
    Modifier
    -0.08
    edes
    -0.08
    upy
    -0.08
    åĪ°æľĢåIJİ
    -0.07
    uell
    -0.07
    гно
    -0.07
    è··
    -0.07
    -inter
    -0.07
    POSITIVE LOGITS
    iment
    0.08
    zza
    0.07
    件
    0.06
     pez
    0.06
    ufer
    0.06
     vét
    0.06
    stein
    0.06
    æĪIJå¥Ĺ
    0.06
    殿åłĤ
    0.06
    ience
    0.06
    Activations Density 0.001%

    No Known Activations