© 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. 59056
    Prev
    Next
    INDEX
    Explanations

    fixed or predetermined condition

    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
    nÄĻ
    -0.07
    _fds
    -0.07
    wein
    -0.07
    çļĦæŃ£å¸¸
    -0.07
    ihen
    -0.07
    venirs
    -0.07
    éĴ
    -0.07
    ç«ŀäºī对æīĭ
    -0.07
    tg
    -0.07
    kah
    -0.07
    POSITIVE LOGITS
    åĽºå®ļ
    0.20
    åĽºå®ļçļĦ
    0.19
     fixed
    0.19
    fixed
    0.18
     Fixed
    0.17
    Fixed
    0.17
    -fixed
    0.16
    _fixed
    0.16
    åĽºå®ļåľ¨
    0.15
     already
    0.14
    Activations Density 0.083%

    No Known Activations