© 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. 587
    Prev
    Next
    INDEX
    Explanations

    section beginnings

    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
     Interracial
    -0.37
    -Owned
    -0.32
     fkk
    -0.32
     Erotic
    -0.30
     Unsure
    -0.29
    :";č↵
    -0.29
    -Methods
    -0.28
    ,www
    -0.28
     :";↵
    -0.27
    :;↵
    -0.26
    POSITIVE LOGITS
     The
    0.41
     There
    0.38
     As
    0.33
     When
    0.32
     While
    0.32
     Although
    0.32
     This
    0.31
     In
    0.31
     We
    0.31
    The
    0.31
    Activations Density 3.532%

    No Known Activations