© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11017
    Prev
    Next
    INDEX
    Explanations

    leading-order contributions

    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
    éĶ¡
    -0.08
    éķIJ
    -0.07
    à¸ķาà¸ģ
    -0.07
    addock
    -0.07
    rams
    -0.07
    লà§įপ
    -0.07
    ReadOnly
    -0.07
    _PROVID
    -0.06
    æĪĸçĶ±
    -0.06
     suss
    -0.06
    POSITIVE LOGITS
     xạ
    0.09
    ç²Ĵ
    0.08
    æ±Łæ¹ĸ
    0.08
    jj
    0.08
    ç¢İ
    0.07
    ãģķãģ¾
    0.07
     Umberto
    0.07
    jem
    0.07
     distributions
    0.07
    udit
    0.07
    Activations Density 0.010%

    No Known Activations