© 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. 1471
    Prev
    Next
    INDEX
    Explanations

    equations and formulas

    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
     yarg
    -0.27
    SCO
    -0.24
    swers
    -0.24
    '&&
    -0.23
    ,www
    -0.23
     Publié
    -0.23
    twor
    -0.23
    rary
    -0.23
    ificate
    -0.22
    regunta
    -0.22
    POSITIVE LOGITS
     equation
    0.32
     equations
    0.29
     formula
    0.28
    å¼ı
    0.24
    åħ¬å¼ı
    0.23
    å¼ıçļĦ
    0.22
     defining
    0.22
     rewritten
    0.22
    eq
    0.22
     expression
    0.21
    Activations Density 0.283%

    No Known Activations