© 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. 3617
    Prev
    Next
    INDEX
    Explanations

    informational texts

    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
    peater
    -0.23
    (parseFloat
    -0.22
    eated
    -0.21
    :async
    -0.21
    è´
    -0.21
    untime
    -0.21
    -await
    -0.20
    amework
    -0.20
    "><?=$
    -0.20
    []={
    -0.20
    POSITIVE LOGITS
     scaleY
    0.24
    ãģªãģĦãģ§ãģĻ
    0.23
    ï¼ģï¼ģ↵↵
    0.22
    ç»ıéªĮåĢ¼
    0.21
    纰
    0.21
     lehet
    0.20
     fucks
    0.20
    éĺ¿æ£®
    0.19
    classnames
    0.19
    lijah
    0.19
    Activations Density 0.043%

    No Known Activations