© 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. 60914
    Prev
    Next
    INDEX
    Explanations

    lattice simulations, Monte Carlo, numerical simulations

    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
     mx
    -0.07
     vạch
    -0.07
     конÑĨеÑĢ
    -0.07
     Iranians
    -0.06
    tero
    -0.06
     onstage
    -0.06
    轻轻ä¸Ģ
    -0.06
    PERT
    -0.06
    mx
    -0.06
    iction
    -0.06
    POSITIVE LOGITS
    åĽĽçĤ¹
    0.08
    anela
    0.08
    æł¼åŃIJ
    0.08
     Kud
    0.08
     ren
    0.07
    èµģ
    0.07
    .ff
    0.07
    labs
    0.07
    迪æĸ¯
    0.07
     мониÑĤоÑĢ
    0.07
    Activations Density 0.006%

    No Known Activations