© 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. 55194
    Prev
    Next
    INDEX
    Explanations

    film titles including "Paris" or "The Last"

    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
    å¾Ĺä¸Ĭ
    -0.06
    åĴĮæľī
    -0.06
    å¸Ĥ容
    -0.05
     Eq
    -0.05
    ç®ķ
    -0.05
    èĩ³æĸ¼
    -0.05
    -linux
    -0.05
    éĤ¸
    -0.05
    awns
    -0.05
    æ¯Ķçħ§
    -0.05
    POSITIVE LOGITS
    é¼İé¼İ
    0.08
    isha
    0.08
    åĬłè½½æĽ´å¤ļ
    0.08
    ä»ij
    0.08
     diserta
    0.08
    inless
    0.08
    _increment
    0.08
    uvad
    0.08
    zze
    0.08
    OBO
    0.08
    Activations Density 0.050%

    No Known Activations