© 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. 1804
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    BASEPATH
    -0.25
    __':č↵
    -0.25
    \",↵
    -0.24
     StringSplitOptions
    -0.24
    ')");↵
    -0.24
    [".
    -0.24
     Playoff
    -0.23
     Horny
    -0.23
    %";↵
    -0.23
    \"",↵
    -0.23
    POSITIVE LOGITS
    ""
    0.28
    ",
    0.24
     none
    0.23
     ""
    0.23
    "↵
    0.23
    "
    0.23
    allee
    0.23
    none
    0.21
     fray
    0.21
    RouterModule
    0.20
    Activations Density 3.008%

    No Known Activations