© 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. 555
    Prev
    Next
    INDEX
    Explanations

    to be

    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
    ãİľ
    -0.26
    çļĦ带é¢Ĩ
    -0.24
    æŁ¥çľĭåħ¨æĸĩ
    -0.23
    apons
    -0.22
     (![
    -0.22
    -scenes
    -0.20
    åŀ§
    -0.20
    åİĨåı²æĸ°
    -0.20
    æijĨæĶ¾
    -0.19
     بذÙĦÙĥ
    -0.19
    POSITIVE LOGITS
    åıijçĶŁåľ¨
    0.51
     occur
    0.36
     occurs
    0.35
     happening
    0.31
     occurred
    0.31
    çļĦåıijçĶŁ
    0.30
     occurring
    0.29
    ä½ĵçİ°åľ¨
    0.28
    oc
    0.26
    æºIJäºİ
    0.26
    Activations Density 4.520%

    No Known Activations