© 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. 3483
    Prev
    Next
    INDEX
    Explanations

    application or boot

    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
    agara
    -0.20
     bead
    -0.19
     parachute
    -0.19
    oord
    -0.19
    lam
    -0.18
    骢
    -0.18
    singleton
    -0.17
    ophil
    -0.17
     singleton
    -0.17
    æ²¥éĿĴ
    -0.17
    POSITIVE LOGITS
    kek
    0.23
     авг
    0.22
    BootApplication
    0.21
    ä¸ŃåĽ½ç½ij游
    0.21
    noinspection
    0.21
    .setVertical
    0.21
    æĬ¿
    0.20
    æĹĦ
    0.20
    ASHBOARD
    0.20
    çİ«
    0.20
    Activations Density 0.001%

    No Known Activations