© 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. 128
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
    ç¥Ľæĸij
    -0.36
     deltaTime
    -0.28
    -NLS
    -0.27
     Posté
    -0.27
    âľ·
    -0.26
    èĪ·
    -0.26
     bindActionCreators
    -0.25
     deltaX
    -0.25
     dumpsters
    -0.25
     deltaY
    -0.24
    POSITIVE LOGITS
    å¿ĥå¾Ĺä½ĵä¼ļ
    0.30
    æĪķ
    0.28
    è¿ĶåĽŀæIJľçĭIJ
    0.28
    ç´łè´¨æķĻèĤ²
    0.28
    游æĪıæĵįä½ľ
    0.28
    rvine
    0.28
    åľ¨çݩ家
    0.28
    åħ¬å¼Ģ课
    0.27
    æľīçļĦçݩ家
    0.27
    æĸ°æµªè´¢ç»ı
    0.27
    Activations Density 1.084%

    No Known Activations