© 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. 287
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
     ($('#
    -0.25
     ($("#
    -0.24
     Gebä
    -0.23
    dae
    -0.20
    :async
    -0.19
    æıł
    -0.19
     initState
    -0.19
    ESIS
    -0.19
    VOKE
    -0.19
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.19
    POSITIVE LOGITS
    /WebAPI
    0.23
    FunctionFlags
    0.22
    ulfilled
    0.21
    extérieur
    0.21
    afi
    0.21
    .userInteractionEnabled
    0.20
    opsy
    0.20
    ycz
    0.20
    omy
    0.19
    ymm
    0.19
    Activations Density 0.062%

    No Known Activations