© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3858
    Prev
    Next
    INDEX
    Explanations

    next

    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
    pery
    -0.28
    olkata
    -0.26
    åĶIJå®ĩ
    -0.24
    æĿ¨æ¬¢
    -0.24
    Ngu
    -0.24
    uebas
    -0.23
     sodom
    -0.23
    acters
    -0.23
    volución
    -0.23
    gota
    -0.22
    POSITIVE LOGITS
    ä»İæł¹æľ¬
    0.34
     next
    0.31
    /MPL
    0.29
    next
    0.29
    åı¯ä»¥æĽ´å¥½
    0.28
    缸åħ³è´Łè´£
    0.25
    å¿ħä¸įåı¯
    0.24
    趿
    0.23
    æĢ§ä»·
    0.23
    éĿŀ常æĺİæĺ¾
    0.23
    Activations Density 0.049%

    No Known Activations