© 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. 25368
    Prev
    Next
    INDEX
    Explanations

    phenotype, plasticity, handicap

    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
    hurst
    -0.09
    ritz
    -0.08
    aci
    -0.08
    ç´¯äºĨ
    -0.07
    bers
    -0.07
    çļĦæīĭæ³ķ
    -0.07
    éĩijæĽ²
    -0.07
    好书
    -0.07
    管æīĢ
    -0.07
    amment
    -0.07
    POSITIVE LOGITS
     phenotype
    0.09
    æݩ饰
    0.09
    æİ©çĽĸ
    0.08
    _display
    0.07
     mascher
    0.07
    åıªçľĭ
    0.07
    /display
    0.06
    éĿ¢è²Į
    0.06
    masked
    0.06
    éķ¿åŁİ
    0.06
    Activations Density 0.001%

    No Known Activations