© 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. 222
    Prev
    Next
    INDEX
    Explanations

    was

    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
    ergus
    -0.26
    ings
    -0.26
    Haunted
    -0.26
     now
    -0.25
    tings
    -0.25
    leftJoin
    -0.24
     currently
    -0.24
     NOW
    -0.24
    ê²IJ
    -0.24
    now
    -0.23
    POSITIVE LOGITS
    /is
    0.37
     formerly
    0.36
     originally
    0.36
     recently
    0.32
     previously
    0.31
     earlier
    0.31
     yesterday
    0.30
    hế
    0.28
    /Dk
    0.27
    formerly
    0.26
    Activations Density 2.885%

    No Known Activations