© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3513
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    eshire
    -0.22
     CircularProgress
    -0.21
     girlfriends
    -0.20
    +"<
    -0.20
    },č↵č↵
    -0.20
    rades
    -0.20
     avaliações
    -0.20
     prosec
    -0.20
     GtkWidget
    -0.20
    潸
    -0.20
    POSITIVE LOGITS
    Nguá»ĵn
    0.22
    ä¸Ģèĩ´å¥½è¯Ħ
    0.21
    è°ĭ
    0.20
    ä¼łåĩº
    0.20
    .rot
    0.20
    èĥª
    0.20
    人身
    0.19
     èĭ¥è¦ģ
    0.19
    able
    0.18
    ulle
    0.18
    Activations Density 0.002%

    No Known Activations