© 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. 13034
    Prev
    Next
    INDEX
    Explanations

    MazdaSpeed6, apps crash, engineering helm

    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
    Ïģιν
    -0.07
    åıĸèĢĮ代ä¹ĭ
    -0.07
    æĪijæħ¢
    -0.07
    æ¯İ
    -0.07
    (calc
    -0.07
     Wenger
    -0.07
    åĽłæѤèĢĮ
    -0.07
    è°Ĩ
    -0.06
    çīį
    -0.06
    amal
    -0.06
    POSITIVE LOGITS
    äºĶæĺ¯
    0.07
    ä¹ĭä¸Ģå°±æĺ¯
    0.07
    类似çļĦ
    0.07
     certas
    0.07
     Kemen
    0.06
     vs
    0.06
     certos
    0.06
    stech
    0.06
    ocha
    0.06
    çļĦå°±æĺ¯
    0.06
    Activations Density 0.017%

    No Known Activations