© 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. 1756
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     GANG
    -0.26
     {?>↵
    -0.24
    ÑĢоÑģл
    -0.22
     Cleaner
    -0.22
     onCancelled
    -0.22
     Depths
    -0.21
    çĦī
    -0.21
    пÑĥÑģ
    -0.20
    Į¨
    -0.20
    pNet
    -0.20
    POSITIVE LOGITS
    REFERRED
    0.23
    cá
    0.20
    terdam
    0.19
    PickerController
    0.19
     "-";↵
    0.19
    -court
    0.18
     ifndef
    0.18
    dbuf
    0.18
    ']=="
    0.18
    .Toolkit
    0.18
    Activations Density 0.234%

    No Known Activations