© 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. 477
    Prev
    Next
    INDEX
    Explanations

    location prepositions

    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
    ".↵↵↵↵
    -0.25
    éĵ©
    -0.24
    /Dk
    -0.24
    âĸ¿
    -0.23
    ãĥµ
    -0.23
     discrepan
    -0.21
     vö
    -0.21
    ?type
    -0.21
    ?"↵↵↵↵
    -0.20
    CrLf
    -0.20
    POSITIVE LOGITS
     in
    0.66
     within
    0.55
     on
    0.47
     inside
    0.46
    à¹ĥà¸Ļ
    0.44
    within
    0.43
     trong
    0.42
    åľ¨æĪijçļĦ
    0.41
     across
    0.40
    åľ¨
    0.40
    Activations Density 9.640%

    No Known Activations