© 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. 2090
    Prev
    Next
    INDEX
    Explanations

    Polish universities

    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
    Ẽ
    -0.24
    olicited
    -0.23
    icorn
    -0.23
    æķī
    -0.23
    étude
    -0.22
    "struct
    -0.21
    ÄĴ
    -0.21
     ());↵↵
    -0.21
     prostituer
    -0.21
    ponge
    -0.21
    POSITIVE LOGITS
    ifestyles
    0.25
    à¹Į
    0.23
    [sizeof
    0.22
    etu
    0.21
     UClass
    0.21
    ){}↵
    0.21
    é
    0.21
    Ðģ
    0.21
    Ö
    0.21
    Ùĭ
    0.21
    Activations Density 0.572%

    No Known Activations