© 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. 1310
    Prev
    Next
    INDEX
    Explanations

    allow

    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
    //=
    -0.30
    bió
    -0.25
    Serviço
    -0.23
     tô
    -0.23
    .MouseDown
    -0.23
    ".↵↵↵↵
    -0.23
    ornment
    -0.22
    @include
    -0.22
     negó
    -0.22
     ());↵↵
    -0.21
    POSITIVE LOGITS
     ApplicationException
    0.28
    å¿ħä¸įåı¯
    0.25
    ä»İæł¹æľ¬
    0.25
     Fucking
    0.24
     kontakt
    0.24
    ãģĵãģ¨ãģĮå¤ļãģĦ
    0.24
    为äºĨæĽ´å¥½
    0.23
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.23
     konk
    0.23
     yPos
    0.23
    Activations Density 9.181%

    No Known Activations