© 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. 2141
    Prev
    Next
    INDEX
    Explanations

    names of places and organizations

    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
     "
    -0.23
    ,
    -0.22
    -0.21
     ide
    -0.21
     (
    -0.21
     im
    -0.21
     P
    -0.21
     l
    -0.21
    :
    -0.20
    ↵
    -0.20
    POSITIVE LOGITS
     *</
    0.27
    xfff
    0.26
    /Dk
    0.26
    (IService
    0.26
    -strokes
    0.25
    TreeWidgetItem
    0.24
    ðŁĺī
    0.24
     Ø£ÙģرÙĬ
    0.24
     erotica
    0.23
    VERTISE
    0.23
    Activations Density 0.436%

    No Known Activations