© 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. 3965
    Prev
    Next
    INDEX
    Explanations

    item labels

    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
    TestFixture
    -0.20
    ;display
    -0.20
    yclerview
    -0.19
    åIJĽåŃIJ
    -0.18
     }};↵
    -0.18
    çĿģå¼Ģ
    -0.18
    ãĥ¬ãĤ¹
    -0.18
    باب
    -0.18
     wrapped
    -0.18
    Enumeration
    -0.17
    POSITIVE LOGITS
    ltre
    0.20
    æľĭåıĭ们对
    0.20
    å®ŀçĶ¨
    0.20
    nels
    0.20
    âĢ¾
    0.19
    },č↵č↵
    0.19
     Manual
    0.19
     SolidColorBrush
    0.19
    %"><
    0.19
    ç½ijç«Ļåľ°åĽ¾
    0.19
    Activations Density 0.211%

    No Known Activations