© 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. 766
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas or code

    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
    ëł´
    -0.08
    ä¸Ģéĥİ
    -0.08
    Ùĥت
    -0.08
    urang
    -0.07
    før
    -0.07
    মান
    -0.07
    éĹĬ
    -0.07
    ething
    -0.07
    nella
    -0.07
    assic
    -0.07
    POSITIVE LOGITS
    utkan
    0.07
    aces
    0.07
    Ŀ
    0.07
    å°ıæīĭ
    0.06
    鹤
    0.06
    éļĻ
    0.06
    меÑģÑĤи
    0.06
    fors
    0.06
    ELS
    0.06
    ucch
    0.06
    Activations Density 0.005%

    No Known Activations