© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3591
    Prev
    Next
    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tempList
    -0.23
    w
    -0.21
    j
    -0.21
    示æĦı
    -0.20
    èµ°åĬ¿åĽ¾
    -0.20
    æł·çļĦ
    -0.20
     undef
    -0.19
    å¸Ĥå§Ķ书记
    -0.19
    ãģĻãĤĭãģĵãģ¨ãģĮãģ§ãģįãģ¾ãģĻ
    -0.19
    -0.19
    POSITIVE LOGITS
     fkk
    0.29
    .Microsoft
    0.24
    egis
    0.24
    AXB
    0.24
    inality
    0.24
    ".↵↵↵↵
    0.23
    ,},↵
    0.23
    Aceptar
    0.23
    .biz
    0.23
    obao
    0.23
    Activations Density 0.001%

    No Known Activations