© 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. 12762
    Prev
    Next
    INDEX
    Explanations

    sports scores and statistics

    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
    ote
    -0.08
    大éĺµ
    -0.07
    èĢĮåIJĮ
    -0.07
     seger
    -0.07
    æĻ®éĢļä¼ļåijĺ
    -0.07
     Verz
    -0.07
    ORY
    -0.06
    ysi
    -0.06
    éĺµ
    -0.06
    oin
    -0.06
    POSITIVE LOGITS
    å°±å¤ļ
    0.07
    à´ŁàµĨ
    0.07
    å½ĵæŶçļĦ
    0.07
    æĮij
    0.06
    ÃŃn
    0.06
     اخ
    0.06
    ãĥĢãĥĸãĥ«
    0.06
    çŃ·åŃIJ
    0.06
    ingo
    0.06
    chas
    0.06
    Activations Density 0.001%

    No Known Activations