© 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. 2617
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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
    defgroup
    -0.19
    illisecond
    -0.19
    ookies
    -0.19
    redients
    -0.19
    aturday
    -0.18
    éĴį
    -0.18
    /ay
    -0.18
     века
    -0.18
    imest
    -0.18
    FontAwesome
    -0.18
    POSITIVE LOGITS
     Interracial
    0.22
    åŁºæľ¬ä¸Ĭéĥ½
    0.22
    :Boolean
    0.21
     Barton
    0.21
    ç®Ģ
    0.20
    æ®ĥ
    0.20
    æĤ±
    0.20
    :both
    0.20
    :pointer
    0.19
    .ObjectModel
    0.19
    Activations Density 0.024%

    No Known Activations