© 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. 2964
    Prev
    Next
    INDEX
    Explanations

    prob

    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
    çļĦ带é¢Ĩ
    -0.24
    æĹıèĩªæ²»
    -0.23
     pstmt
    -0.23
    scrição
    -0.21
    解æĶ¾æĢĿæĥ³
    -0.21
     xOffset
    -0.20
    纰
    -0.20
    são
    -0.20
    éĵij
    -0.20
     random
    -0.20
    POSITIVE LOGITS
    oggler
    0.22
    indow
    0.22
    damn
    0.22
    PasswordField
    0.22
    <path
    0.22
    =findViewById
    0.22
    ="<<
    0.21
     tü
    0.21
    emd
    0.21
    /Area
    0.21
    Activations Density 0.005%

    No Known Activations