© 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. 2756
    Prev
    Next
    INDEX
    Explanations

    books

    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
    ;set
    -0.25
    *******************************************************************************/↵
    -0.23
    intendent
    -0.23
     ARTICLE
    -0.22
     fkk
    -0.22
     backpage
    -0.22
     LENG
    -0.22
    ,www
    -0.21
    onestly
    -0.21
    çı
    -0.21
    POSITIVE LOGITS
     textbook
    0.30
     textbooks
    0.29
    æķĻæĿIJ
    0.29
    书ç±į
    0.29
     book
    0.28
     standard
    0.27
     books
    0.26
    book
    0.25
     classic
    0.25
     reference
    0.24
    Activations Density 0.106%

    No Known Activations