© 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. 439
    Prev
    Next
    INDEX
    Explanations

    usage conditions

    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
    åĴĮ
    -0.35
     and
    -0.35
     &
    -0.31
    æĢ§åĴĮ
    -0.30
     or
    -0.29
    æĪĸ
    -0.27
     и
    -0.26
    åĴĮä»ĸçļĦ
    -0.26
     vÃł
    -0.25
    åĴĮæľįåĬ¡
    -0.25
    POSITIVE LOGITS
     alike
    0.31
    ;set
    0.30
    ¡´
    0.27
    awei
    0.26
    nze
    0.26
    ä¸ŃåĽ½ç½ij游
    0.25
    -await
    0.25
     burge
    0.25
    ;display
    0.24
    ewise
    0.24
    Activations Density 3.087%

    No Known Activations