© 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. 8229
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions and conjectures

    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
    èī
    -0.07
    imismo
    -0.06
    ousand
    -0.06
    éļıä¹ĭ
    -0.06
    /perl
    -0.06
    åķ
    -0.06
    èķ
    -0.06
    åIJĮæŶè¿ĺè¦ģ
    -0.06
     '^
    -0.06
     sall
    -0.06
    POSITIVE LOGITS
    ervas
    0.08
    ocha
    0.07
    året
    0.07
     undergoing
    0.07
    viste
    0.07
    年以ä¸ĬçļĦ
    0.07
    ìĿ´ëĿ¼ëıĦ
    0.07
    ÑĻа
    0.07
    ä»»ä½ķä¿Ŀè¯ģ
    0.07
     ÙĪÙĦÙĬ
    0.07
    Activations Density 0.060%

    No Known Activations