© 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. 44123
    Prev
    Next
    INDEX
    Explanations

    spatio-temporal data or dimensions

    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
    èĢĹ
    -0.07
    é¡¿äºĨé¡¿
    -0.07
    ä¹ŀ
    -0.07
    æijĨ设
    -0.06
    é£
    -0.06
    åºķåŃIJ
    -0.06
    æĹ©é¤IJåIJİ
    -0.06
     Um
    -0.06
    ä¸Ģåı£æ°Ķ
    -0.06
    æijĨ
    -0.06
    POSITIVE LOGITS
    instanc
    0.10
    EMBER
    0.09
    ripper
    0.08
    åįķåħĥæł¼
    0.08
    otime
    0.08
     ÑıÑĩей
    0.07
    irem
    0.07
    ROWS
    0.07
    ÑĥÑĢо
    0.07
    .nz
    0.07
    Activations Density 0.062%

    No Known Activations