© 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. 1265
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     '".
    -0.26
    .parseFloat
    -0.26
    	throws
    -0.26
    "nil
    -0.26
    foundland
    -0.25
     '/');↵
    -0.24
    Ø£ÙĪض
    -0.24
     '/')
    -0.23
    ;');↵
    -0.23
    __).
    -0.23
    POSITIVE LOGITS
     "
    0.65
    ("
    0.50
    “
    0.47
     “
    0.45
    "
    0.44
     '
    0.40
    “(
    0.39
    ="
    0.38
    ãĢĮ
    0.38
     «
    0.38
    Activations Density 1.437%

    No Known Activations