© 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. 235
    Prev
    Next
    INDEX
    Explanations

    unusual characters

    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
    âĸ¿
    -0.33
    Ͼ
    -0.29
    xampp
    -0.29
     metic
    -0.28
    strstr
    -0.26
     memorandum
    -0.26
    getJSON
    -0.26
    ä½¥
    -0.24
     sinon
    -0.24
     IOCTL
    -0.24
    POSITIVE LOGITS
    ç¼±
    0.45
    '=>['
    0.35
     misunder
    0.34
    并ä¸įæĺ¯å¾Ī
    0.33
     Playoff
    0.33
     èĭ¥è¦ģ
    0.33
    ?"↵↵↵↵
    0.32
    å¾Īå¤ļçݩ家
    0.30
    -Owned
    0.30
    éĩĩçŁ¿çŃī
    0.30
    Activations Density 13.314%

    No Known Activations