© 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. 25163
    Prev
    Next
    INDEX
    Explanations

    php script variables

    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
    åĴĮç¾İåĽ½
    -0.06
    aro
    -0.06
    ncy
    -0.06
    æīĢåľ¨çļĦ
    -0.06
     ::
    -0.06
    amer
    -0.06
    æ¸Ĭ
    -0.06
    ä¾¦çł´
    -0.06
    宿
    -0.06
    æĸĩåѦå¥ĸ
    -0.06
    POSITIVE LOGITS
    êu
    0.09
    aliz
    0.08
    izz
    0.08
    atriz
    0.08
    ourney
    0.07
    иÑģÑĥ
    0.07
    axter
    0.07
    azer
    0.07
     озна
    0.07
    astas
    0.07
    Activations Density 0.056%

    No Known Activations