© 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. 149
    Prev
    Next
    INDEX
    Explanations

    calculations or definitions

    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
    ornings
    -0.28
     dealloc
    -0.27
    elmet
    -0.22
    etxt
    -0.22
    Descricao
    -0.21
    avigate
    -0.21
    elerik
    -0.21
    /operator
    -0.20
    izabeth
    -0.20
    upported
    -0.20
    POSITIVE LOGITS
    FontAwesomeIcon
    0.24
     Erectile
    0.23
    æĸ¹æĸ¹éĿ¢
    0.23
     ImageIcon
    0.22
     Erot
    0.22
     Surg
    0.21
     irresist
    0.21
    _verts
    0.21
     selfies
    0.21
    éķŀ
    0.21
    Activations Density 0.269%

    No Known Activations