© 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-CHAT-65K
    7. 46200
    Prev
    Next
    INDEX
    Explanations

    code string manipulation

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elmet
    -0.20
    affer
    -0.20
    amt
    -0.19
    ymous
    -0.19
    iales
    -0.18
    aeda
    -0.18
    itesse
    -0.18
    htub
    -0.18
    elite
    -0.18
    .VisualBasic
    -0.17
    POSITIVE LOGITS
     Fer
    0.19
    糧
    0.19
    LBL
    0.18
    丸
    0.18
    /Footer
    0.18
    bote
    0.18
    culos
    0.18
    JoinColumn
    0.18
    ----------č↵
    0.17
    ä½ıæĪ·
    0.17
    Activations Density 0.001%

    No Known Activations