© 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. 22367
    Prev
    Next
    INDEX
    Explanations

    dancing on the Ceiling

    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
    ALAR
    -0.08
    ty
    -0.08
    æĦ
    -0.07
    iket
    -0.07
    otá
    -0.07
     impe
    -0.07
    athing
    -0.07
    .mb
    -0.07
    _requires
    -0.06
     Roe
    -0.06
    POSITIVE LOGITS
    presso
    0.08
    ou
    0.08
    ouz
    0.07
    对åIJ§
    0.07
    AJ
    0.07
    undra
    0.07
    برد
    0.07
    èݱåĿŀ
    0.07
     Benson
    0.07
    åĽŀ
    0.07
    Activations Density 0.378%

    No Known Activations