© 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. 19164
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and questions

    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´£ç¼ĸ
    -0.07
    ollen
    -0.07
    olla
    -0.07
     Putri
    -0.07
    ìĿµ
    -0.07
    ouce
    -0.06
     Frem
    -0.06
    itsu
    -0.06
    anness
    -0.06
     ÙĪجÙĩ
    -0.06
    POSITIVE LOGITS
    <decltype
    0.08
    ç´¢
    0.08
    eros
    0.07
    ardo
    0.07
    _optional
    0.07
    ç©Į
    0.07
    大èĥĨçļĦ
    0.07
     jat
    0.07
    å·¢
    0.07
    ार
    0.07
    Activations Density 0.087%

    No Known Activations