© 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. 3393
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    说å®ŀ
    -0.22
    -strokes
    -0.19
    ();++
    -0.19
    minent
    -0.19
    åķģ
    -0.19
    èij³
    -0.19
     Lyon
    -0.18
    ACHINE
    -0.18
    atel
    -0.18
    ä¸Ńç§ij
    -0.18
    POSITIVE LOGITS
    (strpos
    0.23
    éªľ
    0.21
    keterangan
    0.20
    _Abstract
    0.20
    .getSeconds
    0.20
    SetActive
    0.20
    //↵↵↵
    0.20
    thèque
    0.20
    .getMinutes
    0.19
    .generic
    0.19
    Activations Density 0.002%

    No Known Activations