© 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. 1992
    Prev
    Next
    INDEX
    Explanations

    relationship

    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
    :frame
    -0.25
    :normal
    -0.24
    ,strlen
    -0.23
    _deinit
    -0.22
    æľĭåıĭ们对
    -0.22
     RaisePropertyChanged
    -0.20
    .vertx
    -0.20
    :System
    -0.20
    ();++
    -0.20
    POSITIVE LOGITS
     between
    0.58
    åıĮæĸ¹
    0.56
    between
    0.56
    ä¹ĭéĹ´çļĦ
    0.54
    å½¼æѤ
    0.52
     Between
    0.50
    ä¹ĭéĹ´
    0.48
     mutual
    0.48
    åħ³ç³»
    0.48
    _between
    0.47
    Activations Density 4.891%

    No Known Activations