© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 473
    Prev
    Next
    INDEX
    Explanations

    code or symbols

    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
    纰
    -0.34
     lowes
    -0.29
    è¡Ģ液循çݯ
    -0.28
     sublicense
    -0.27
    家éĥ½çŁ¥éģĵ
    -0.27
    akening
    -0.27
     scaleY
    -0.26
     usern
    -0.26
    ç¥Ľæĸij
    -0.26
    缸åħ³è´Łè´£
    -0.26
    POSITIVE LOGITS
     fkk
    0.34
    .CustomButton
    0.33
     Interracial
    0.32
    DMETHOD
    0.31
    /Dk
    0.31
    ,application
    0.31
    çļĦ带é¢Ĩ
    0.31
     Ä°n
    0.30
     Millenn
    0.28
    @update
    0.28
    Activations Density 4.292%

    No Known Activations