© 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. 3131
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
    好åĿı
    -0.21
    çĽ¸ä¼´
    -0.21
    ifie
    -0.19
    stdarg
    -0.19
    kul
    -0.18
    ("`
    -0.17
     doch
    -0.17
    asper
    -0.17
    CCCCCC
    -0.17
    .Desc
    -0.17
    POSITIVE LOGITS
    /Instruction
    0.24
    ooter
    0.23
     meisje
    0.22
     ));č↵
    0.21
    orget
    0.21
    家éĥ½çŁ¥éģĵ
    0.21
     {{--<
    0.21
    :CGRect
    0.21
    xdc
    0.21
    unsch
    0.20
    Activations Density 0.002%

    No Known Activations