© 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. 3396
    Prev
    Next
    INDEX
    Explanations

    advantage

    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
    ediator
    -0.31
    beits
    -0.25
    puties
    -0.24
    puty
    -0.22
    arshal
    -0.22
    ubyte
    -0.21
    .rmi
    -0.21
    ÈĻi
    -0.21
     agré
    -0.20
    visor
    -0.20
    POSITIVE LOGITS
    detalle
    0.26
    ä¼ĺåĬ¿
    0.24
    åľ°ä½į
    0.23
    çļĦä¼ĺåĬ¿
    0.23
    åĬ£åĬ¿
    0.21
    koneksi
    0.21
    äºĴè¡¥
    0.21
     Aç
    0.21
    åĽĽä¸ªèĩªä¿¡
    0.21
    entially
    0.21
    Activations Density 0.313%

    No Known Activations