© 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. 33591
    Prev
    Next
    INDEX
    Explanations

    mathematical or code 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
    å°½åľ¨
    -0.09
    IMER
    -0.07
    ä¿¡
    -0.07
    itaire
    -0.07
    YPE
    -0.07
     bufsize
    -0.07
    ález
    -0.07
    orman
    -0.07
    ción
    -0.07
    AGEN
    -0.07
    POSITIVE LOGITS
    à¹Ģà¸Ĺ
    0.07
    åĽłä¸ºè¿Ļ个
    0.07
    éĻ¤æģ¶
    0.06
    Âł
    0.06
    åĽłä¸º
    0.06
    飻
    0.06
    ม
    0.06
     ÙĪÙİÙĦ
    0.06
     Knox
    0.06
    infer
    0.06
    Activations Density 0.011%

    No Known Activations