© 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. 28472
    Prev
    Next
    INDEX
    Explanations

    `zsSysVersionMsg_t` structure

    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
    cesi
    -0.08
    urgi
    -0.07
    zeg
    -0.07
    mium
    -0.07
    ean
    -0.07
    缴åij¼
    -0.07
    ÑĢÑĥд
    -0.07
    osh
    -0.07
    URRE
    -0.07
    ÙĬدÙĩ
    -0.07
    POSITIVE LOGITS
    ams
    0.07
    åIJ¯
    0.07
    樱
    0.07
    åĪĨä¹ĭ
    0.07
    ably
    0.07
    å¼¥
    0.07
     Aub
    0.06
    è¾ŀ
    0.06
    åıł
    0.06
    éĢĤ
    0.06
    Activations Density 0.238%

    No Known Activations