© 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. 28634
    Prev
    Next
    INDEX
    Explanations

    numeric digits and Roman numerals

    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¿Ļéģĵ
    -0.06
    /html
    -0.06
    -
    -0.06
    olean
    -0.06
    æķĪ
    -0.06
    onas
    -0.06
    à¹Īาà¸ĩ
    -0.06
    /change
    -0.06
     наÑĢ
    -0.06
    quir
    -0.06
    POSITIVE LOGITS
     (...)
    0.08
    ibaldi
    0.07
    åıŃ
    0.07
    ãģİ
    0.07
    ({...
    0.07
    ayette
    0.07
    å¿ĹæĦ¿æľįåĬ¡éĺŁ
    0.07
    иÑģло
    0.07
     ones
    0.07
    åľ¨æŁIJ
    0.07
    Activations Density 0.041%

    No Known Activations