© 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. 3602
    Prev
    Next
    INDEX
    Explanations

    word fragments

    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
    .InnerException
    -0.27
    ç«
    -0.23
    形象
    -0.20
     اÙĦعرا
    -0.19
     Abs
    -0.19
     NONINFRINGEMENT
    -0.19
    è°Ĺ
    -0.19
    ë´ħ
    -0.19
    }->{
    -0.19
     Jeb
    -0.19
    POSITIVE LOGITS
    resa
    0.22
     rencont
    0.20
    éĿ©æĸ°
    0.20
    nier
    0.20
    ete
    0.19
    itionally
    0.19
    ktion
    0.19
    iferay
    0.18
     Rosenberg
    0.18
    çIJ²
    0.18
    Activations Density 0.001%

    No Known Activations