© 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. 2192
    Prev
    Next
    INDEX
    Explanations

    1

    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
    çĽijåIJ¬é¡µéĿ¢
    -0.27
    (strpos
    -0.24
    akter
    -0.23
    _delegate
    -0.21
    ptune
    -0.21
     (![
    -0.20
    braska
    -0.20
    ighborhood
    -0.20
     STATES
    -0.20
    :Any
    -0.19
    POSITIVE LOGITS
    âĪ½
    0.22
    تÙĥÙĪÙĨ
    0.20
     consect
    0.19
    IntArray
    0.19
    CommandEvent
    0.19
    ÙħÙĨØ°
    0.19
     "','
    0.18
    .OS
    0.18
    isty
    0.18
    æĹ©
    0.18
    Activations Density 0.266%

    No Known Activations