© 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. 1450
    Prev
    Next
    INDEX
    Explanations

    intact

    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
    :Event
    -0.26
    /↵↵↵↵
    -0.25
    (MethodImplOptions
    -0.22
    />.
    -0.22
    bruar
    -0.22
    typeparam
    -0.21
    anoia
    -0.21
    möglich
    -0.21
    ederland
    -0.20
    uggage
    -0.20
    POSITIVE LOGITS
    ä¿ĿæĮģçĿĢ
    0.44
    ä¸įåıĺ
    0.43
     intact
    0.41
     unchanged
    0.41
    继ç»Ń
    0.38
     remained
    0.36
     remain
    0.34
     continue
    0.32
    ä¿ĿæĮģ
    0.32
     remains
    0.31
    Activations Density 2.199%

    No Known Activations