© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3909
    Prev
    Next
    INDEX
    Explanations

    code programming

    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
    _tD
    -0.27
    ãģĻãģĵãģ¨
    -0.22
    serter
    -0.22
    _tA
    -0.21
     (*)(
    -0.20
    (*)(
    -0.20
    .paging
    -0.19
     mapDispatchToProps
    -0.19
     xsi
    -0.19
     initWithStyle
    -0.18
    POSITIVE LOGITS
    .yang
    0.24
    仲
    0.23
    %@",
    0.22
    manda
    0.21
    çIJ
    0.20
    ä¸ĭæĿ¥
    0.20
    FTER
    0.20
    avigate
    0.20
    uibModal
    0.20
    eded
    0.19
    Activations Density 0.043%

    No Known Activations