© 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. 59982
    Prev
    Next
    INDEX
    Explanations

    constant

    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
    ï¸ı
    -0.07
    -0.07
    -0.06
    ï¸İ
    -0.06
    åĴ³
    -0.06
    ÙĬÙĨ
    -0.06
     hom
    -0.06
    wad
    -0.06
     sen
    -0.06
    æľ¬ç«ĻæīĢæľī
    -0.06
    POSITIVE LOGITS
    Äįas
    0.07
    xada
    0.07
    abr
    0.07
    üt
    0.07
     sacked
    0.07
    ÛĮرÙĩ
    0.07
    arking
    0.07
    opan
    0.07
    iris
    0.07
    á»ĺI
    0.07
    Activations Density 0.278%

    No Known Activations