© 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. 1337
    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
     namoro
    -0.32
     Hardcore
    -0.32
    æį¢åı¥è¯Ŀ
    -0.31
    e
    -0.27
     jó
    -0.27
     sovere
    -0.26
     Naughty
    -0.26
     culo
    -0.26
     erotica
    -0.26
    ç»Ń约
    -0.26
    POSITIVE LOGITS
    :'.$
    0.48
    :".$
    0.41
    "value
    0.40
    Hôtel
    0.39
    ;;;;;;;;
    0.38
    ä½ıæĪ¿åħ¬ç§¯
    0.38
    ksam
    0.37
    flen
    0.36
    iets
    0.36
    æľīæľŁå¾Ĵ
    0.35
    Activations Density 50.318%

    No Known Activations