© 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. 12256
    Prev
    Next
    INDEX
    Explanations

    corrections or disagreements

    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
    chnik
    -0.07
    ucher
    -0.07
    uhn
    -0.07
     Heard
    -0.07
    åIJ¬è¯´
    -0.07
    λιÏĥ
    -0.06
    æį®è¯´
    -0.06
    omat
    -0.06
     Ef
    -0.06
    ège
    -0.06
    POSITIVE LOGITS
    itat
    0.08
     conclus
    0.07
    èĪĬ
    0.07
    ä¸Ĭä¸Ģç¯ĩ
    0.07
    .Excel
    0.07
    =>'
    0.07
    æĬµæĬĹåĬĽ
    0.07
    ä¸ŃæĮĩåĩº
    0.06
     palp
    0.06
    羿
    0.06
    Activations Density 0.003%

    No Known Activations