© 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. 1158
    Prev
    Next
    INDEX
    Explanations

    according to

    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
    loquent
    -0.21
     JADX
    -0.21
    solete
    -0.20
     //
    -0.20
     programma
    -0.20
    PropTypes
    -0.19
    -invalid
    -0.19
    EEDED
    -0.19
    è¯Ĥ
    -0.19
    åħĭæĢĿ
    -0.19
    POSITIVE LOGITS
     ×Ķ×ķ×ĵ
    0.32
     geile
    0.23
    WillAppear
    0.23
     __________________↵↵
    0.22
     enthusi
    0.21
    ------+------+
    0.21
     UIAlert
    0.20
    ((&
    0.20
     ikea
    0.20
    ()){
    0.20
    Activations Density 0.731%

    No Known Activations