© 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. 37694
    Prev
    Next
    INDEX
    Explanations

    directions and positions

    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
     comm
    -0.07
    Wr
    -0.07
    åĮĸåIJį
    -0.06
    .tap
    -0.06
    athers
    -0.06
    wr
    -0.06
    åĮĸäºĨ
    -0.06
    pector
    -0.06
    åĬ¨çĿĢ
    -0.06
    ä¸įå®Į
    -0.06
    POSITIVE LOGITS
    igy
    0.07
    ONTAL
    0.07
    ãĢģ
    0.07
    axy
    0.07
    middle
    0.07
    缴è¡Į
    0.07
    ç¢
    0.07
    ENDO
    0.07
    byss
    0.07
     middle
    0.07
    Activations Density 0.033%

    No Known Activations