© 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. 42627
    Prev
    Next
    INDEX
    Explanations

    computations involving mod

    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
    STS
    -0.08
    åľ¨è¥¿
    -0.07
    ëĤ©
    -0.07
    ç¯Ĩ
    -0.06
     unint
    -0.06
    XML
    -0.06
    渡
    -0.06
    адÑĮ
    -0.06
    uzzi
    -0.06
    erti
    -0.06
    POSITIVE LOGITS
    éĿ¶
    0.08
    /target
    0.08
     targetType
    0.08
    ç²īç¢İæľº
    0.07
    awe
    0.07
    seau
    0.07
    itto
    0.07
    _VALIDATE
    0.07
     Target
    0.07
     residual
    0.07
    Activations Density 0.013%

    No Known Activations