© 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. 25150
    Prev
    Next
    INDEX
    Explanations

    Python function calls and arguments

    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
    etag
    -0.06
    ade
    -0.06
    alach
    -0.06
    /ion
    -0.06
    æŃ£å¤§
    -0.06
    ×ijר×Ļ×Ŀ
    -0.06
    ä¸ĢèĪ¬æĥħåĨµä¸ĭ
    -0.06
    epad
    -0.06
    çİĭå°ı
    -0.06
    åIJĽå®ī
    -0.06
    POSITIVE LOGITS
    trys
    0.09
    irements
    0.08
    zens
    0.08
    köz
    0.08
    ล
    0.08
    enseur
    0.08
    å°Ķ夫
    0.07
    ienz
    0.07
    czyn
    0.07
    itters
    0.07
    Activations Density 0.003%

    No Known Activations