© 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. 3074
    Prev
    Next
    INDEX
    Explanations

    containing

    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
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.24
    /Dk
    -0.22
    IBC
    -0.21
     Según
    -0.20
    AtPath
    -0.20
    ágenes
    -0.20
    readcr
    -0.20
    OUS
    -0.20
    PTY
    -0.20
    éĥĦ
    -0.20
    POSITIVE LOGITS
    åIJ«
    0.31
     contain
    0.23
    åIJ«æľī
    0.23
     contained
    0.22
    êtes
    0.21
    åĮħåIJ«
    0.21
    æĭ¥æľī
    0.21
     contiene
    0.20
    cons
    0.20
     './../
    0.20
    Activations Density 0.859%

    No Known Activations