© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2446
    Prev
    Next
    INDEX
    Explanations

    city

    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
    çľģå§Ķ
    -0.23
    èĽĩ
    -0.22
    çľģåĨħ
    -0.22
    åħ¨çľģ
    -0.21
     Kur
    -0.20
     appDelegate
    -0.20
    æĪijçľģ
    -0.20
    åIJĦçľģ
    -0.20
     states
    -0.20
    csrf
    -0.19
    POSITIVE LOGITS
    -city
    0.31
    /Dk
    0.29
     city
    0.28
     dikke
    0.28
    .City
    0.27
    iffany
    0.27
     Millenn
    0.26
    city
    0.26
    nqu
    0.26
     CITY
    0.25
    Activations Density 0.607%

    No Known Activations