© 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. 3316
    Prev
    Next
    INDEX
    Explanations

    code and software licenses

    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
    ica
    -0.20
    æĿŀ
    -0.19
     Directed
    -0.19
    ç§į
    -0.19
    icken
    -0.19
    èĦ²
    -0.19
    bai
    -0.19
     MADE
    -0.19
    çĹ¢
    -0.19
    ÙĦÙĤ
    -0.19
    POSITIVE LOGITS
    '=>['
    0.27
    ensibly
    0.24
    %X
    0.24
     },↵↵↵
    0.21
    ä½ıæĪ¿åħ¬ç§¯
    0.21
    gnore
    0.20
     oko
    0.20
    entic
    0.20
    thinkable
    0.20
    %x
    0.20
    Activations Density 0.010%

    No Known Activations