© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 918
    Prev
    Next
    INDEX
    Explanations

    prime factors

    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
     UINavigationController
    -0.20
     Falk
    -0.20
    utherford
    -0.19
     physicists
    -0.19
     wij
    -0.18
    ảo
    -0.18
     '-')↵
    -0.18
     UsersController
    -0.18
    .EventSystems
    -0.18
    newValue
    -0.18
    POSITIVE LOGITS
    /Dk
    0.29
    _MetaData
    0.25
     prime
    0.24
    )((((
    0.24
    )];↵↵
    0.23
     factors
    0.23
     gcd
    0.23
    Factors
    0.22
    .removeAttribute
    0.22
    ]='\
    0.21
    Activations Density 0.435%

    No Known Activations