© 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. 412
    Prev
    Next
    INDEX
    Explanations

    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
     ('$
    -0.27
    \OptionsResolver
    -0.26
     strncmp
    -0.25
     strchr
    -0.25
    =@"
    -0.24
     strncpy
    -0.24
    .epam
    -0.24
     scaleX
    -0.23
    são
    -0.22
     Borough
    -0.22
    POSITIVE LOGITS
    SFML
    0.25
    åħļæĢ»
    0.23
     array
    0.23
    ç½ijç«Ļé¦ĸ页
    0.23
    éĻ£
    0.21
    âĺħâĺħ
    0.21
    mund
    0.21
    :focus
    0.21
    iode
    0.21
    ATRIX
    0.20
    Activations Density 1.625%

    No Known Activations