© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31596
    Prev
    Next
    INDEX
    Explanations

    PHP/JS/C keywords and HTML tags

    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
    人æĦı
    -0.07
    esses
    -0.06
    ifies
    -0.06
     поÑĤе
    -0.06
    éĿ¢æĹł
    -0.06
    xxx
    -0.06
     appunto
    -0.06
    ause
    -0.06
    df
    -0.06
    auge
    -0.06
    POSITIVE LOGITS
    éĺħè¯»æľ¬æĸĩåīį
    0.09
    ï¼įï¼įï¼įï¼į
    0.08
     natomiast
    0.07
     inoltre
    0.07
    echos
    0.07
    orem
    0.07
    abit
    0.07
     ÄijÃłnh
    0.07
    âĺħâĺĨ
    0.07
    éĻ¤æѤ
    0.07
    Activations Density 0.586%

    No Known Activations