© 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. 1764
    Prev
    Next
    INDEX
    Explanations

    u variations

    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
    ðŁļ©
    -0.28
    éļıæŶéļı
    -0.27
    }elseif
    -0.27
    --------------------------------------------------------------------------↵
    -0.26
     unfavor
    -0.24
     ê·¸ê²ĥìĿĢ
    -0.24
    对çħ§æ£ĢæŁ¥
    -0.24
    æĤ»
    -0.23
    æĢ§ä»·
    -0.23
    åľ¨æ¸¸æĪıä¸Ń
    -0.23
    POSITIVE LOGITS
    ltra
    0.32
    swire
    0.31
    abyrin
    0.31
    isex
    0.29
    indered
    0.28
    ifestyles
    0.28
    iferay
    0.28
    ÙĦاÙĤات
    0.28
    anmar
    0.27
    ICTURE
    0.27
    Activations Density 8.609%

    No Known Activations