© 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. 979
    Prev
    Next
    INDEX
    Explanations

    M words

    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
    anship
    -0.40
    undos
    -0.39
    ônica
    -0.38
    ONTAL
    -0.36
    تÙĦÙĥ
    -0.33
    ówi
    -0.32
    ILLISE
    -0.30
    ÃŃstica
    -0.29
    ODULE
    -0.29
    ysqli
    -0.28
    POSITIVE LOGITS
    ornings
    0.51
     Madness
    0.36
    ESSAGES
    0.34
    endoza
    0.32
    emento
    0.29
     Mondays
    0.29
    عÙĦÙĪÙħات
    0.28
    سؤ
    0.27
    جÙħÙĪع
    0.26
     mẽ
    0.26
    Activations Density 5.293%

    No Known Activations