© 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. 57454
    Prev
    Next
    INDEX
    Explanations

    specific kinds of shipwreck

    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
    zil
    -0.08
    haupt
    -0.07
    hirts
    -0.07
    ä¹ĭäºİ
    -0.07
    اتب
    -0.06
     dụ
    -0.06
    abbo
    -0.06
    ÑĤоÑĢа
    -0.06
    /master
    -0.06
    缼
    -0.06
    POSITIVE LOGITS
     presumably
    0.08
    åĨħ容æĺ¯
    0.08
    ä¸ĢèĤ¡
    0.07
    ãģĦãĤī
    0.07
    ä¸ĢåĪĩçļĦ
    0.07
    pres
    0.07
    çº¿åĽ¾
    0.07
    çĿ«æ¯Ľ
    0.07
    éļı便
    0.07
    eil
    0.07
    Activations Density 0.001%

    No Known Activations