© 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. 25416
    Prev
    Next
    INDEX
    Explanations

    monoclinic, hexagonal, cubic crystal structures

    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
    ä¸İç»´ä¿®
    -0.08
    æ±ķ
    -0.08
    墩
    -0.08
    è¡ĮéĹ´
    -0.08
    çĨł
    -0.08
    integral
    -0.07
    abouts
    -0.07
    ç»ıæµİåѦ
    -0.07
     integral
    -0.07
    ])==
    -0.07
    POSITIVE LOGITS
     casse
    0.07
     dumb
    0.06
    大èĢĮ
    0.06
    deps
    0.06
    avery
    0.06
    ä¼ij
    0.06
    amarca
    0.06
    xis
    0.06
    alleries
    0.06
    pthread
    0.06
    Activations Density 0.004%

    No Known Activations