© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14042
    Prev
    Next
    INDEX
    Explanations

    diophantine equations and inequalities

    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
    atee
    -0.07
    çĦ¦åĮĸ
    -0.07
    utate
    -0.07
    丧失
    -0.07
     Sheridan
    -0.07
    åĸª
    -0.06
    ãĥĨãĥ¼ãĤ¸
    -0.06
    leston
    -0.06
    ä»ĺãģij
    -0.06
    reeze
    -0.06
    POSITIVE LOGITS
    ä¸įå®ļ
    0.08
     satisfied
    0.08
    æľīå¿Ĺ
    0.07
    amic
    0.07
    éģ¿åħįåĩºçİ°
    0.07
    åѦçłĶ究
    0.07
    çĪ±æĪij
    0.07
    icy
    0.07
     favourite
    0.06
     solver
    0.06
    Activations Density 0.002%

    No Known Activations