© 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. 1109
    Prev
    Next
    INDEX
    Explanations

    research and analysis

    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
     ðŁ
    -0.35
    管æݧ
    -0.32
    ç²¾åĩĨ
    -0.32
     impactful
    -0.32
    utterstock
    -0.32
     https
    -0.31
     incentiv
    -0.30
    -0.29
     tasked
    -0.29
    缸è¾ĥäºİ
    -0.29
    POSITIVE LOGITS
    âĦł
    0.32
    irlines
    0.29
    iéndo
    0.29
    å¿ĥå¾Ĺä½ĵä¼ļ
    0.28
     daÃŁ
    0.28
     Incontri
    0.28
    -scalable
    0.28
    âīĥ
    0.27
    rvine
    0.27
    !!");↵
    0.26
    Activations Density 19.552%

    No Known Activations