© 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. 1612
    Prev
    Next
    INDEX
    Explanations

    code elements

    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
    кÑĨион
    -0.21
    æĿª
    -0.20
    纡
    -0.19
    alyzed
    -0.19
     resp
    -0.19
     formal
    -0.19
    æĬ±ä½ı
    -0.19
     tor
    -0.18
    åĽ½äº§
    -0.18
     eh
    -0.18
    POSITIVE LOGITS
     addCriterion
    0.24
    ICTURE
    0.23
    traî
    0.23
    :animated
    0.22
    #af
    0.22
    ATYPE
    0.22
    '/>
    0.21
    ergency
    0.21
    ")));
    0.21
     Gratuit
    0.21
    Activations Density 3.238%

    No Known Activations