© 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. 1611
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
    YTE
    -0.23
    .getSeconds
    -0.22
    QRSTUV
    -0.21
    åľ¾
    -0.21
    _msgs
    -0.20
     Tib
    -0.20
     strtoupper
    -0.20
    |array
    -0.19
    iscrim
    -0.19
    æĥ³èµ·æĿ¥
    -0.19
    POSITIVE LOGITS
    İ·
    0.23
    __);
    0.21
    meye
    0.20
    æŁ¥éªĮ
    0.20
    ç©¿æIJŃ
    0.19
    é¾ĩ
    0.19
    DownList
    0.19
    //:
    0.19
    解æĶ¾æĢĿæĥ³
    0.19
    *size
    0.19
    Activations Density 0.005%

    No Known Activations