© 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. 1706
    Prev
    Next
    INDEX
    Explanations

    sports

    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
    é»ijæģ¶
    -0.38
    ä¸įèī¯ä¿¡æģ¯
    -0.34
     Dems
    -0.34
    åľ¨çݩ家ä¸Ń
    -0.32
     Knicks
    -0.31
    ä»ħ次
    -0.31
    纰
    -0.30
     modalitÃł
    -0.29
     maneu
    -0.29
     novitÃł
    -0.29
    POSITIVE LOGITS
    æĢ§ä»·
    0.36
    âĦī
    0.33
    hores
    0.29
    ç´łæĻ´
    0.28
    åĹ¥
    0.27
    è¿Ļ款车
    0.26
     cornerback
    0.26
     homers
    0.25
     winger
    0.25
    åħ«å¤§ä»¥æĿ¥
    0.25
    Activations Density 4.269%

    No Known Activations