© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 794
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    æŁ¥çľĭ详æĥħ
    -0.29
     nouve
    -0.28
    âĺij
    -0.27
    %";↵
    -0.27
    âĺİ
    -0.26
    ðŁĵĮ
    -0.26
    åıĭæĥħéĵ¾æİ¥
    -0.26
    FLASH
    -0.26
    BOSE
    -0.26
    æĸ°åĬł
    -0.25
    POSITIVE LOGITS
    odiac
    0.40
    abbix
    0.37
    ephy
    0.35
    ormsg
    0.32
    isoner
    0.31
    etroit
    0.31
    ombies
    0.30
    mercial
    0.30
    egree
    0.29
    lexible
    0.29
    Activations Density 11.472%

    No Known Activations