© 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. 1745
    Prev
    Next
    INDEX
    Explanations

    elections

    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
     imgUrl
    -0.29
     Pics
    -0.27
     Clintons
    -0.25
     lawmaker
    -0.24
    /animations
    -0.23
     glyphicon
    -0.22
     erotica
    -0.22
     imageURL
    -0.22
    complexContent
    -0.22
     oko
    -0.22
    POSITIVE LOGITS
    åĢĻéĢī人
    0.29
     election
    0.26
    éĢī举
    0.25
     pornstar
    0.23
     elections
    0.23
    (/^\
    0.22
     elect
    0.22
    elect
    0.22
     unic
    0.22
     candidate
    0.22
    Activations Density 1.459%

    No Known Activations