© 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. 3647
    Prev
    Next
    INDEX
    Explanations

    non-standard characters

    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
    arseille
    -0.20
    mainwindow
    -0.20
    erts
    -0.20
    );">↵
    -0.19
    unta
    -0.19
    åij½
    -0.19
    vang
    -0.19
     conting
    -0.18
    utura
    -0.18
    .WinForms
    -0.18
    POSITIVE LOGITS
    /*↵
    0.26
    åľ®
    0.22
    uran
    0.21
    èĪ«
    0.21
    âļĹ
    0.21
    ðŁĵIJ
    0.21
    ]){
    0.20
    keiten
    0.20
     RedirectTo
    0.19
    UILabel
    0.19
    Activations Density 0.005%

    No Known Activations