© 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. 2442
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     butterknife
    -0.22
    ampa
    -0.21
    è¡°
    -0.20
    áºĴ
    -0.20
    oriously
    -0.20
     CIS
    -0.19
     Michaels
    -0.19
    Seleccione
    -0.19
    \Catalog
    -0.19
     sometimes
    -0.18
    POSITIVE LOGITS
    줬
    0.29
    leanor
    0.25
    èĿ°
    0.23
    ynet
    0.22
    ãĢĴ
    0.21
    ,Th
    0.20
    íĦ¸
    0.20
    --------------------------------------------------------------------------↵
    0.20
    /Peak
    0.20
     Sweep
    0.19
    Activations Density 0.003%

    No Known Activations