© 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. 2768
    Prev
    Next
    INDEX
    Explanations

    documentation tags

    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
    herits
    -0.26
    ysz
    -0.24
    &view
    -0.23
    pai
    -0.23
    :["
    -0.23
    emp
    -0.20
    çij¢
    -0.20
    iyor
    -0.20
    istes
    -0.20
    imary
    -0.20
    POSITIVE LOGITS
     pathMatch
    0.20
    èĩªè´¸åĮº
    0.20
     Diamond
    0.20
     sub
    0.20
    ahrung
    0.20
    ðŁĮ°
    0.19
     automát
    0.19
     hop
    0.19
    pesan
    0.19
    intendent
    0.18
    Activations Density 0.211%

    No Known Activations