© 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. 65157
    Prev
    Next
    INDEX
    Explanations

    url or code context

    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
    ç½ijç«Ļå¤ĩæ¡Ī
    -0.08
    viders
    -0.07
    odr
    -0.07
    keh
    -0.07
    ÑĢаÑĤно
    -0.07
     misk
    -0.07
     оÑĤм
    -0.07
    æĹłåīį
    -0.07
    çī¹åĪ«å¥½
    -0.07
    oola
    -0.07
    POSITIVE LOGITS
    ëijIJ
    0.06
    ä¸įåĸĦ
    0.06
    å··
    0.06
    ç»ıèIJ¥æĢ§
    0.06
    éŁ¿
    0.06
    åĺ¿
    0.06
    hes
    0.06
    ä½
    0.06
    hek
    0.06
    mb
    0.05
    Activations Density 0.001%

    No Known Activations