© 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. 22104
    Prev
    Next
    INDEX
    Explanations

    calculate greatest common divisor

    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
    ĤŃ
    -0.07
    å¤ĸåŀĭ
    -0.07
    ikov
    -0.07
    ãĥµ
    -0.07
    å¤ĦçIJĨæĸ¹æ³ķ
    -0.07
    ungsk
    -0.07
    æĹ¶ä¸º
    -0.07
    assa
    -0.07
    égorie
    -0.06
    ä¾
    -0.06
    POSITIVE LOGITS
    ix
    0.07
    æīĢéľĢçļĦ
    0.07
    isky
    0.07
    alani
    0.07
    judge
    0.07
    çĿ¡åīį
    0.07
    #
    0.07
    eluk
    0.07
    çĦļ
    0.07
    éŀŃ
    0.07
    Activations Density 0.014%

    No Known Activations