© 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. 48063
    Prev
    Next
    INDEX
    Explanations

    fractions of different values

    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
    lm
    -0.08
    çݯçIJĥç½ij
    -0.07
    åľ¨ä¸Ģå®ļ
    -0.07
     treated
    -0.07
    æĺİçıł
    -0.07
    åĬ©çIJĨ
    -0.06
    æľĢé«ĺçļĦ
    -0.06
    çļĦæľĢé«ĺ
    -0.06
    大ä¼ļåłĤ
    -0.06
    ::__
    -0.06
    POSITIVE LOGITS
    fraction
    0.07
    eterminate
    0.07
     fraction
    0.07
    uhan
    0.07
    ags
    0.07
    vision
    0.07
    åĺİ
    0.07
     fractions
    0.07
    äºijé£ŀ
    0.07
     Äįasu
    0.07
    Activations Density 0.006%

    No Known Activations