© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 1951
    Prev
    Next
    INDEX
    Explanations

    code paths and filenames

    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
    计æŶ
    -0.07
     timed
    -0.06
    ilm
    -0.06
     nighttime
    -0.06
    près
    -0.06
     livest
    -0.06
    æ±²
    -0.06
    ัà¸ģ
    -0.06
    am
    -0.06
    赡
    -0.06
    POSITIVE LOGITS
    oun
    0.08
    ç½ijé¦ĸ页
    0.07
    éĩij森
    0.07
    æĮĤäºĨ
    0.07
    kees
    0.07
     สà¸ģุล
    0.07
    à¤Łà¤¾
    0.07
    ycop
    0.07
    toMatchSnapshot
    0.07
    ICOS
    0.07
    Activations Density 0.779%

    No Known Activations