© 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. 3746
    Prev
    Next
    INDEX
    Explanations

    code and technical

    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
    ä¸ĸ家
    -0.23
    abcdefghijkl
    -0.19
    ree
    -0.19
    },č↵č↵
    -0.19
     FUCK
    -0.19
     WebDriverWait
    -0.19
     derp
    -0.19
     Mes
    -0.19
    stral
    -0.18
    кÑĤив
    -0.18
    POSITIVE LOGITS
    -END
    0.27
    '&&
    0.24
    åIJįåĪĹåīį
    0.23
    AsStringAsync
    0.22
    æĿ¥çľĭçľĭåIJ§
    0.21
    æĵIJ
    0.21
    outil
    0.21
    -Headers
    0.21
    éļıæŶéļı
    0.20
    --------------------------------------------------------------------------↵
    0.20
    Activations Density 0.206%

    No Known Activations