© 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. 1742
    Prev
    Next
    INDEX
    Explanations

    Apache

    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
    aternity
    -0.34
    gency
    -0.31
    radient
    -0.29
    ookies
    -0.29
    æį¢åı¥è¯Ŀ
    -0.28
    redient
    -0.28
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.28
    IGHL
    -0.27
    pson
    -0.27
    rawer
    -0.27
    POSITIVE LOGITS
    ÙĪضÙĪع
    0.27
    -Pacific
    0.26
     данном
    0.23
    лÑĮÑĤ
    0.23
    nowled
    0.22
    ından
    0.22
    ın
    0.21
    loys
    0.21
    æĢİä¹ĪåĽŀäºĭ
    0.21
    åĭĥåĭĥ
    0.20
    Activations Density 6.129%

    No Known Activations