© 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. 813
    Prev
    Next
    INDEX
    Explanations

    classification proposal

    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
    >--
    -0.25
    FontAwesomeIcon
    -0.24
    家éĥ½çŁ¥éģĵ
    -0.23
    åĶ·
    -0.23
     fkk
    -0.22
    ç¡ķ士çłĶ究
    -0.22
    -Cs
    -0.21
    -UA
    -0.21
    .EventQueue
    -0.21
    .='
    -0.21
    POSITIVE LOGITS
     multimedia
    0.20
     end
    0.20
    ORMAT
    0.19
    æµģ失
    0.19
     indent
    0.19
    èīı
    0.18
    ļ
    0.18
    éŀ¯
    0.18
     parcel
    0.18
    yp
    0.18
    Activations Density 0.001%

    No Known Activations