© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1437
    Prev
    Next
    INDEX
    Explanations

    location and direction

    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
    hores
    -0.44
     sodom
    -0.29
    çĹ¼
    -0.28
    åħļé£İ
    -0.26
    æ¡İ
    -0.25
    è¯ģåĪ¸æĬķèµĦ
    -0.24
    æĭĽèĤ¡
    -0.24
    ä¸ĵ项æĸĹäºī
    -0.23
    æºĺ
    -0.23
    举æĸ¹è´¢å¯Į
    -0.23
    POSITIVE LOGITS
    æľīæľŁå¾Ĵ
    0.30
     htonl
    0.24
     strtol
    0.24
    _Tick
    0.23
    åIJįæ°Ķ
    0.23
    主è¦ģéĽĨä¸Ń
    0.23
    é«Ģ
    0.23
     (*((
    0.23
    ');↵↵↵↵
    0.23
    çļĦç¼ĺ
    0.23
    Activations Density 4.495%

    No Known Activations