© 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. 1607
    Prev
    Next
    INDEX
    Explanations

    names and events

    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
     createState
    -0.21
    vero
    -0.21
    ntity
    -0.21
    usercontent
    -0.21
    ristol
    -0.20
    .apiUrl
    -0.20
    pecting
    -0.19
    /Dk
    -0.19
    AMPL
    -0.18
    iams
    -0.18
    POSITIVE LOGITS
     RectTransform
    0.22
    éĴľ
    0.19
    çķ¥
    0.19
     consulate
    0.18
    ):?>↵
    0.18
    =<?=$
    0.18
    libft
    0.18
    prowad
    0.18
    ewidth
    0.18
     f
    0.17
    Activations Density 0.001%

    No Known Activations