© 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. 2447
    Prev
    Next
    INDEX
    Explanations

    necessary

    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
     tantra
    -0.26
    CLUDING
    -0.24
    åĪĽæĸ°èĥ½åĬĽ
    -0.23
    çļĦ带é¢Ĩ
    -0.23
     incontri
    -0.22
    éĩįè¦ģåĽłç´ł
    -0.22
     TMPro
    -0.22
     Tantra
    -0.21
     annonces
    -0.21
    æĽ´å¤ļä¿¡æģ¯
    -0.20
    POSITIVE LOGITS
    iếu
    0.24
    bilt
    0.23
    yms
    0.23
    oftware
    0.22
    iết
    0.21
    REFERRED
    0.21
    ulings
    0.20
    ypes
    0.20
    egov
    0.20
    igsaw
    0.20
    Activations Density 0.151%

    No Known Activations