© 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. 214
    Prev
    Next
    INDEX
    Explanations

    months

    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
    erk
    -0.22
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.22
    emi
    -0.20
     èĩªåĬ¨çĶŁæĪIJ
    -0.19
    memberOf
    -0.19
    ãĥģãĥ£ãĥ¼
    -0.19
    /*****************************************************************************↵
    -0.19
     christmas
    -0.19
    éĺī
    -0.19
    lève
    -0.19
    POSITIVE LOGITS
    -scalable
    0.24
    ãĢĤwww
    0.24
    :green
    0.23
     lowes
    0.23
    ายà¸Ļ
    0.23
    MBER
    0.22
     Marriott
    0.22
    .scalajs
    0.22
     kuk
    0.22
    -valu
    0.22
    Activations Density 0.779%

    No Known Activations