© 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. 15491
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions or expressions

    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
    è¦ģæĿ¥
    -0.07
    enor
    -0.07
    ç¿ħ
    -0.07
    egl
    -0.06
    ëĭ¹
    -0.06
     Neh
    -0.06
    æł©
    -0.06
    à¹Īาà¸ĩ
    -0.06
    oses
    -0.06
     Grosso
    -0.06
    POSITIVE LOGITS
    ầm
    0.08
    emez
    0.08
    ä¸įçĿĢ
    0.07
     rint
    0.07
    InstanceState
    0.07
    ColumnType
    0.07
    xada
    0.07
    undler
    0.07
    raten
    0.07
    isti
    0.07
    Activations Density 0.003%

    No Known Activations