© 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. 3204
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    ÑģлÑĥÑĪа
    -0.21
     gamm
    -0.20
     createElement
    -0.20
    è°ĥåĬ¨
    -0.19
    imus
    -0.18
    ãĥµ
    -0.18
     Hilton
    -0.18
     ‘
    -0.18
    ãģªãĤĬ
    -0.18
    frican
    -0.17
    POSITIVE LOGITS
    iffany
    0.26
    vla
    0.23
    pike
    0.23
    建档ç«ĭ
    0.23
    berapa
    0.22
    arching
    0.22
    lest
    0.22
    utta
    0.21
     bacheca
    0.21
    yyyyMMdd
    0.21
    Activations Density 0.001%

    No Known Activations