© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 880
    Prev
    Next
    INDEX
    Explanations

    code and technical

    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
    agascar
    -0.27
    建档ç«ĭ
    -0.25
    ãĤĵãģĺãĤĥãģªãģĦãģĭ
    -0.24
     !***
    -0.23
    põe
    -0.23
    -0.23
     dieta
    -0.22
    -Speed
    -0.22
     strikeouts
    -0.22
    å¤įå·¥å¤į
    -0.22
    POSITIVE LOGITS
    .SingleOrDefault
    0.29
    æĪķ
    0.25
    dì
    0.23
    marca
    0.23
    çķ¢ç«Ł
    0.22
    .GridView
    0.22
    ħ
    0.22
    /mainwindow
    0.21
     masturbating
    0.21
    ä¸įèī¯ä¿¡æģ¯
    0.21
    Activations Density 4.311%

    No Known Activations