© 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. 2660
    Prev
    Next
    INDEX
    Explanations

    physics

    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
     dumpsters
    -0.27
     possibly
    -0.22
    估计
    -0.21
    éĢīèĤ¡
    -0.21
     Vuex
    -0.20
    eldo
    -0.20
    avigation
    -0.20
    æĽĻåħī
    -0.20
    大æ¦Ĥ
    -0.20
    æĦį
    -0.20
    POSITIVE LOGITS
    entario
    0.23
    æĭĴä¸į
    0.22
    },č↵č↵
    0.21
    移éĢģ
    0.20
    chap
    0.20
    _rhs
    0.19
    datable
    0.19
    weathermap
    0.19
     Convenience
    0.19
    æĹłåģ¿
    0.19
    Activations Density 0.324%

    No Known Activations