© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4021
    Prev
    Next
    INDEX
    Explanations

    fact or technical term

    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
    åİŁæĸĩåľ°åĿĢ
    -0.22
    .setdefault
    -0.19
    äºĨåįĬ天
    -0.19
     MediaTek
    -0.19
    _Db
    -0.19
    !!)↵
    -0.19
    proxy
    -0.18
    cuador
    -0.17
    Vectorizer
    -0.17
    .getOrElse
    -0.17
    POSITIVE LOGITS
    UILDER
    0.23
    unately
    0.22
    ispens
    0.22
    SizePolicy
    0.21
    iferay
    0.21
    æľĭåıĭ们对
    0.20
    loggedin
    0.20
     ohio
    0.20
    .GenerationType
    0.20
     metab
    0.19
    Activations Density 0.001%

    No Known Activations