© 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. 597
    Prev
    Next
    INDEX
    Explanations

    names

    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
    :normal
    -0.23
    :".$
    -0.21
     createStackNavigator
    -0.21
    atomy
    -0.21
     aver
    -0.20
    uras
    -0.19
    åŁĴ
    -0.19
    èĩ´ãģĹãģ¾ãģĻ
    -0.19
    ä¹łè¿ij
    -0.19
    timeofday
    -0.19
    POSITIVE LOGITS
    udy
    0.19
    AGED
    0.19
     Myers
    0.19
    éric
    0.18
    Ứ
    0.18
    izzo
    0.18
     defenseman
    0.18
    讼
    0.17
     DispatchQueue
    0.17
    posite
    0.17
    Activations Density 0.001%

    No Known Activations