© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1356
    Prev
    Next
    INDEX
    Explanations

    conditions or data

    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
     {}.
    -0.32
    ãĢĤ
    -0.32
    }.
    -0.31
    ++.
    -0.29
     ].
    -0.29
    ''.
    -0.28
     [].
    -0.28
     }.
    -0.28
    ].
    -0.27
    {}.
    -0.27
    POSITIVE LOGITS
    ï¼ĮåĪĻ
    0.37
    ï¼Į请
    0.31
    çļĦ人æĿ¥è¯´
    0.30
    $,
    0.30
    (),
    0.29
     [],
    0.29
     _______,
    0.29
    ',
    0.29
    `,
    0.28
    ",
    0.28
    Activations Density 5.405%

    No Known Activations