© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1303
    Prev
    Next
    INDEX
    Explanations

    text or string

    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
    entiful
    -0.33
    Türkiye
    -0.28
    }());↵
    -0.28
     jihadists
    -0.28
     generado
    -0.27
    游æĪıæĵįä½ľ
    -0.27
     Interracial
    -0.27
     misunder
    -0.26
    BOSE
    -0.26
    ÙĪضÙĪع
    -0.25
    POSITIVE LOGITS
    ToggleButton
    0.28
     and
    0.23
    aData
    0.22
     about
    0.22
    agues
    0.22
     that
    0.21
    WindowState
    0.21
    sembling
    0.21
     verbess
    0.20
    0.20
    Activations Density 8.411%

    No Known Activations