© 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. 554
    Prev
    Next
    INDEX
    Explanations

    code elements

    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
    çĸĸ
    -0.21
     Rencontre
    -0.21
     ?>↵↵↵
    -0.21
    ç¼Ľ
    -0.20
    轫
    -0.20
     desi
    -0.20
    uforia
    -0.20
    phin
    -0.20
    positories
    -0.19
     Burst
    -0.19
    POSITIVE LOGITS
     reife
    0.24
    ührung
    0.23
    åĪ©çĶ¨æĤ¨çļĦ
    0.21
    åĿĽ
    0.21
     CircularProgress
    0.21
     RaisePropertyChanged
    0.20
    abcdefghijklmnop
    0.20
     withStyles
    0.19
    dbo
    0.19
    .ProgressBar
    0.19
    Activations Density 0.359%

    No Known Activations