© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2261
    Prev
    Next
    INDEX
    Explanations

    scientific technical terms

    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
    TestCategory
    -0.21
    ожеÑĤ
    -0.19
    /community
    -0.18
    iser
    -0.18
    @brief
    -0.18
    iele
    -0.18
    åIJŀ
    -0.18
    extrême
    -0.18
    ãĥģãĤ§
    -0.18
    mó
    -0.17
    POSITIVE LOGITS
    hare
    0.25
    -Identifier
    0.25
    processable
    0.25
    lei
    0.23
    uese
    0.23
    -Jul
    0.23
    /↵↵↵↵
    0.22
    ðŁĵIJ
    0.22
    traîn
    0.21
    çĽijåIJ¬é¡µéĿ¢
    0.21
    Activations Density 0.007%

    No Known Activations