© 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. 1103
    Prev
    Next
    INDEX
    Explanations

    prison

    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
     erotica
    -0.28
     masturbating
    -0.28
    _rgba
    -0.27
     bigot
    -0.27
     abducted
    -0.24
     prosecuting
    -0.24
     imgUrl
    -0.23
     Escorts
    -0.23
     suing
    -0.22
     unmist
    -0.22
    POSITIVE LOGITS
    âĦł
    0.33
    两个维æĬ¤
    0.27
    inerary
    0.23
    .getStyle
    0.23
    ]='\
    0.23
    /Area
    0.23
    ’T
    0.23
    (Have
    0.22
     dealloc
    0.22
    ;!
    0.22
    Activations Density 1.775%

    No Known Activations