© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2890
    Prev
    Next
    INDEX
    Explanations

    code and headers

    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
    .VideoCapture
    -0.28
    "';
    -0.26
    >Main
    -0.23
    ÙħÙĤاÙĦات
    -0.23
     поÑĩем
    -0.23
    _HERSHEY
    -0.21
    ASHINGTON
    -0.21
    GuidId
    -0.21
    SHOP
    -0.21
    âľķ
    -0.21
    POSITIVE LOGITS
    åIJĦ
    0.20
    allen
    0.20
    åIJĦåľ°
    0.18
    elon
    0.18
    -floating
    0.18
     conform
    0.18
     swell
    0.18
    >{"
    0.18
    çĿ¹
    0.17
    ÑĨиалÑĮно
    0.17
    Activations Density 0.001%

    No Known Activations