© 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. 135
    Prev
    Next
    INDEX
    Explanations

    sense of

    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
    çĸĸ
    -0.25
    Número
    -0.23
     enthus
    -0.23
    quiries
    -0.23
    lest
    -0.22
    æĸ°æµªè´¢ç»ı
    -0.21
     wholesalers
    -0.21
    responseObject
    -0.20
    <main
    -0.20
    /effects
    -0.20
    POSITIVE LOGITS
    游æĪıéĩĮçļĦ
    0.25
    åĭł
    0.24
    istani
    0.24
    	fflush
    0.24
    exampleInputEmail
    0.23
    istros
    0.23
    .InnerException
    0.23
    ristol
    0.22
     adoles
    0.21
    è¸Ķ
    0.21
    Activations Density 3.423%

    No Known Activations