© 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. 186
    Prev
    Next
    INDEX
    Explanations

    create

    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
    pections
    -0.27
    comings
    -0.27
    IfExists
    -0.26
    нÑıÑĤие
    -0.25
    omanip
    -0.25
    nuts
    -0.25
    becue
    -0.25
    ableObject
    -0.24
    icap
    -0.24
    нÑıÑĤи
    -0.23
    POSITIVE LOGITS
    æĸ°çļĦ
    0.39
    ä¸Ģ个æĸ°çļĦ
    0.38
     new
    0.33
    åİĨåı²æĸ°
    0.29
    à¹ĥหม
    0.28
    äºĨä¸Ģæī¹
    0.27
    new
    0.26
    åĴĮå®ĮåĸĦ
    0.26
     rencont
    0.25
    èĢĮæĪIJ
    0.25
    Activations Density 4.017%

    No Known Activations