© 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. 3398
    Prev
    Next
    INDEX
    Explanations

    undersampling or aggregation

    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
    rium
    -0.07
    åĴĮæ°Ķ
    -0.07
     Khai
    -0.07
    人æĹł
    -0.06
    éŨå¸Ĥ
    -0.06
    éĹº
    -0.06
    ktiv
    -0.06
    ä»ĬçĶŁ
    -0.06
    ç§ijæĬĢåŀĭ
    -0.06
    è°ĥåĬ¨
    -0.06
    POSITIVE LOGITS
     reduction
    0.10
     reduce
    0.10
    Reduce
    0.10
    reduce
    0.09
    缩åĩı
    0.09
     Reduce
    0.09
    缩
    0.09
     downs
    0.09
     Reduction
    0.09
     reducing
    0.09
    Activations Density 0.052%

    No Known Activations