© 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. 914
    Prev
    Next
    INDEX
    Explanations

    so

    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
    -initialized
    -0.33
    trys
    -0.29
    aviours
    -0.29
    erus
    -0.26
    indered
    -0.26
    abbo
    -0.24
    oriously
    -0.23
    roys
    -0.23
    evin
    -0.23
    rarian
    -0.22
    POSITIVE LOGITS
    -called
    0.42
    Türkiye
    0.31
    çļĦ带é¢Ĩ
    0.30
     èĭ¥è¦ģ
    0.28
    ftware
    0.28
    aps
    0.27
    oth
    0.27
    iled
    0.27
    __;
    0.27
    jour
    0.26
    Activations Density 0.498%

    No Known Activations