© 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. 427
    Prev
    Next
    INDEX
    Explanations

    methods and techniques

    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
     practition
    -0.32
    ulfill
    -0.28
    precedented
    -0.24
    assador
    -0.23
     entreprene
    -0.23
    synthesize
    -0.23
     ÑĢеализаÑĨи
    -0.23
    åĽ½éĻħåľ¨çº¿
    -0.22
    phinx
    -0.22
     fontStyle
    -0.22
    POSITIVE LOGITS
    æĸ¹æ³ķ
    0.61
    è¿Ļç§įæĸ¹æ³ķ
    0.60
     method
    0.54
    method
    0.47
     approach
    0.47
     technique
    0.47
     æĸ¹æ³ķ
    0.46
    åĬŀæ³ķ
    0.42
     methods
    0.41
    æĸ¹å¼ı
    0.39
    Activations Density 6.121%

    No Known Activations