© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2590
    Prev
    Next
    INDEX
    Explanations

    numbers mathematical operations

    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
     libertin
    -0.32
    comings
    -0.31
     Tradable
    -0.30
     rotterdam
    -0.30
     Decorating
    -0.29
     Discounts
    -0.29
    ocrats
    -0.28
     vö
    -0.28
     Hardcore
    -0.28
     Millenn
    -0.28
    POSITIVE LOGITS
    æĤ»
    0.25
     кÑĢÑĭÑĪ
    0.25
     '<%=
    0.24
     Ñģдела
    0.24
     NotImplementedException
    0.23
    å¯ŀ
    0.22
    .addData
    0.21
    æĥ´
    0.21
     NotSupportedException
    0.21
    åĹ«
    0.21
    Activations Density 0.426%

    No Known Activations