© 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. 1889
    Prev
    Next
    INDEX
    Explanations

    code arguments

    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
     /*
    -0.27
    /*
    -0.26
    =false
    -0.25
     srand
    -0.23
    ($"
    -0.23
    缸åħ³è´Łè´£
    -0.22
     pestic
    -0.21
     scarc
    -0.21
    (/*
    -0.21
     outputPath
    -0.21
    POSITIVE LOGITS
    kwargs
    0.34
     None
    0.32
    (None
    0.30
    "';
    0.30
     kwargs
    0.28
    None
    0.27
    :;↵
    0.26
    ournaments
    0.26
    _kwargs
    0.26
     practition
    0.25
    Activations Density 1.519%

    No Known Activations