© 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. 2025
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
     AssemblyVersion
    -0.23
    ä¸įå¾Ĺ转载
    -0.22
     bloginfo
    -0.22
    }elseif
    -0.22
    .intellij
    -0.22
    "value
    -0.21
    >NN
    -0.20
     mdi
    -0.20
    åĽĽä¸ªæĦıè¯Ĩ
    -0.20
    "class
    -0.20
    POSITIVE LOGITS
     enough
    0.31
    reste
    0.28
    .AF
    0.26
    ly
    0.26
    iteit
    0.26
    aned
    0.24
    mente
    0.24
     unto
    0.24
     strdup
    0.23
    emente
    0.23
    Activations Density 3.411%

    No Known Activations