© 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. 2695
    Prev
    Next
    INDEX
    Explanations

    continuous

    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
    ÑĤвеÑĢжда
    -0.27
    bsolute
    -0.26
    SharedPtr
    -0.25
    ERSHEY
    -0.24
    engeance
    -0.23
    .setToolTipText
    -0.23
    ÙĤتر
    -0.22
    ahrain
    -0.22
    Sharper
    -0.22
    对åħ¶çľŁå®ŀ
    -0.21
    POSITIVE LOGITS
    ä¸įæĸŃåľ°
    0.26
    ä¸įéĹ´æĸŃ
    0.24
    è¿ŀç»Ń
    0.23
    ä¸įæĸŃçļĦ
    0.23
    exampleInput
    0.23
     continuous
    0.23
     contin
    0.22
     Continuous
    0.22
    ä¸įæĸŃ
    0.22
    üsseldorf
    0.21
    Activations Density 0.274%

    No Known Activations