© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 743
    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
    gambar
    -0.23
    æ°ĺ
    -0.20
    çı²
    -0.20
    воз
    -0.19
     excer
    -0.19
    scrição
    -0.19
     spur
    -0.19
     hoses
    -0.18
    榫
    -0.18
     hose
    -0.18
    POSITIVE LOGITS
    []{↵
    0.26
    /avatar
    0.26
    _Ptr
    0.23
    .AF
    0.23
    printStats
    0.23
    .eql
    0.23
    Slf
    0.22
    JsonValue
    0.22
     bénéficie
    0.21
    {id
    0.21
    Activations Density 0.057%

    No Known Activations