© 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. 632
    Prev
    Next
    INDEX
    Explanations

    technical specific context

    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
    /umd
    -0.25
    elden
    -0.23
    纪å§Ķ书记
    -0.22
    ")));
    -0.21
    +");↵
    -0.20
    -Shirt
    -0.20
    paralleled
    -0.20
    /tos
    -0.20
    uptime
    -0.19
    @student
    -0.19
    POSITIVE LOGITS
    enment
    0.20
    滩
    0.19
    RegularExpression
    0.18
     uchar
    0.18
     NDEBUG
    0.18
     ба
    0.18
     cudaMemcpy
    0.18
     isize
    0.18
    çģ
    0.17
    avigate
    0.17
    Activations Density 0.001%

    No Known Activations