© 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. 1415
    Prev
    Next
    INDEX
    Explanations

    looking/seeing

    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
    olated
    -0.27
    æłī
    -0.26
    澧
    -0.24
     subpo
    -0.23
    itim
    -0.23
     offend
    -0.23
    InputLabel
    -0.23
    æ°Ĺ軽
    -0.23
     dataArray
    -0.23
    busters
    -0.23
    POSITIVE LOGITS
    CLUDING
    0.27
    CAPE
    0.26
    "":
    0.26
    ÑģÑĤолÑĮ
    0.25
    æŁ¥çľĭ详æĥħ
    0.24
    ä¸įèī¯ä¿¡æģ¯
    0.24
    åĬĦ
    0.24
    .eql
    0.24
    ."&
    0.24
    æī®æ¼Ķ游æĪı
    0.24
    Activations Density 9.962%

    No Known Activations