© 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. 482
    Prev
    Next
    INDEX
    Explanations

    models and theory

    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
    âļĹ
    -0.47
    ðŁĵIJ
    -0.44
    âĮĤ
    -0.36
    ðŁĵĻ
    -0.32
     practition
    -0.31
    /sweetalert
    -0.29
    âĹĤ
    -0.28
    __,__
    -0.26
     bureaucr
    -0.26
    صÙĨد
    -0.26
    POSITIVE LOGITS
     model
    0.32
     theory
    0.30
     models
    0.29
     description
    0.26
     systems
    0.25
    模åŀĭ
    0.25
     properties
    0.24
    model
    0.24
    æııè¿°
    0.24
    []=$
    0.24
    Activations Density 1.961%

    No Known Activations