© 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. 29867
    Prev
    Next
    INDEX
    Explanations

    code syntax with variables x and y

    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
     Parade
    -0.08
    éĽį
    -0.08
    cape
    -0.07
    游åŃIJ
    -0.07
    abis
    -0.07
    alink
    -0.07
    å¸ĥå±ĢåĴĮ
    -0.07
    _cpp
    -0.06
    两æĸ¹éĿ¢
    -0.06
    ahari
    -0.06
    POSITIVE LOGITS
    æĸ¯åŁº
    0.07
    idelberg
    0.07
    .unknown
    0.06
    uncul
    0.06
    éŃĦ
    0.06
    à¹ģà¸ķ
    0.06
    解æĶ¾
    0.06
    bec
    0.06
    èĢĮæľī
    0.06
     Advent
    0.06
    Activations Density 0.030%

    No Known Activations