© 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. 279
    Prev
    Next
    INDEX
    Explanations

    technical code context

    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
    æĹłè®ºæĺ¯åħ¶
    -0.38
    æį¢åı¥è¯Ŀ
    -0.34
    çĭ·
    -0.32
     Rihanna
    -0.32
    è¤Ĭ
    -0.32
    以人æ°ij为
    -0.30
    ç»Ń约
    -0.29
    -Owned
    -0.29
    èĵĬ
    -0.28
     latina
    -0.27
    POSITIVE LOGITS
    åĻĢ
    0.36
    é¦Į
    0.35
    ç°ī
    0.32
    åĵ¢
    0.29
    æĿ¥çľĭçľĭåIJ§
    0.29
    åijĸ
    0.28
    建档ç«ĭ
    0.28
    åľ¨çº¿åĴ¨è¯¢
    0.28
    é»ijæģ¶
    0.26
    åĪ¬
    0.26
    Activations Density 40.074%

    No Known Activations