© 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. 3361
    Prev
    Next
    INDEX
    Explanations

    health and business places

    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
     AsyncStorage
    -0.21
    eworthy
    -0.20
     PureComponent
    -0.20
    QueryParam
    -0.20
     onActivityResult
    -0.19
    cosity
    -0.18
     Finals
    -0.18
    èħ§
    -0.18
    opor
    -0.18
    æ¯ıæľĪ
    -0.18
    POSITIVE LOGITS
    çļĦ带é¢Ĩ
    0.23
    '].$
    0.21
    \widgets
    0.21
    åĶ·
    0.20
    zelf
    0.20
     Manor
    0.20
     generado
    0.20
    综åIJĪå®ŀåĬĽ
    0.19
    çĶŁæľº
    0.18
    æĹĸ
    0.18
    Activations Density 0.001%

    No Known Activations