© 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. 2449
    Prev
    Next
    INDEX
    Explanations

    contact information

    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
    赶
    -0.21
     <!--[
    -0.20
    .Ticks
    -0.19
    åıĤä¸İ
    -0.19
     Particip
    -0.19
    <!--[
    -0.19
    .IsFalse
    -0.19
     Brig
    -0.19
    æĸ¯åŁº
    -0.19
    ansen
    -0.18
    POSITIVE LOGITS
    缴è¾ĸ
    0.28
    [email
    0.27
    âĺİ
    0.23
    ">ÃĹ</
    0.20
    _suspend
    0.20
    ä¸Ģè¶Ł
    0.20
    /↵↵↵↵
    0.20
    .writeHead
    0.20
    gambar
    0.19
    .observable
    0.19
    Activations Density 0.121%

    No Known Activations