© 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. 37783
    Prev
    Next
    INDEX
    Explanations

    mathematical notation delimiters

    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
    ARGV
    -0.08
    ONSE
    -0.08
     valer
    -0.07
    rowave
    -0.07
    bliche
    -0.07
    æĹģ
    -0.07
    rina
    -0.07
    ietro
    -0.07
    apo
    -0.07
    æĿ¥æºIJäºİç½ij绾
    -0.07
    POSITIVE LOGITS
    umes
    0.07
    ×ĵ×ķת
    0.07
    words
    0.07
    orman
    0.07
    isman
    0.07
    Weak
    0.06
    สล
    0.06
    éĤ£äºĽ
    0.06
    çĬ¯
    0.06
    cuts
    0.06
    Activations Density 0.003%

    No Known Activations