© 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. 1507
    Prev
    Next
    INDEX
    Explanations

    calculus and series

    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
    persistent
    -0.20
    bic
    -0.20
    wich
    -0.20
    leDb
    -0.19
    tÃŃ
    -0.19
     Larson
    -0.18
    ä¸ĢæŦ
    -0.18
    eut
    -0.18
     persist
    -0.18
    reme
    -0.18
    POSITIVE LOGITS
    limits
    0.26
    åĪ©çĶ¨æĤ¨çļĦ
    0.24
    icens
    0.24
    présent
    0.22
    rvine
    0.22
    *ft
    0.21
    phalt
    0.21
     bloginfo
    0.20
    ä¸Ģéģį
    0.20
    sez
    0.19
    Activations Density 0.146%

    No Known Activations