© 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. 3886
    Prev
    Next
    INDEX
    Explanations

    technical terms and urls

    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
    .sul
    -0.28
    /Branch
    -0.27
    ä¸ĭéĿ¢å°ıç¼ĸ
    -0.27
    ÅĤat
    -0.25
    czÄĻ
    -0.24
     horr
    -0.24
     :";↵
    -0.23
    /Graphics
    -0.23
    .ecore
    -0.23
    æݨä»ĭä¼ļ
    -0.23
    POSITIVE LOGITS
     agréable
    0.33
     EXEMPLARY
    0.29
     Rencontres
    0.29
     Crushing
    0.27
     Relatives
    0.26
    tá
    0.25
    printStats
    0.25
     GÅĤ
    0.25
    ãģ«ãģªãĤĮ
    0.25
    å®īãģı
    0.25
    Activations Density 2.364%

    No Known Activations