© 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. 1046
    Prev
    Next
    INDEX
    Explanations

    scientific or 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
     }}"><
    -0.23
    çĹŀ
    -0.22
     ))}↵
    -0.21
    enn
    -0.19
    omp
    -0.19
     Worse
    -0.19
    \base
    -0.18
     }}">
    -0.18
    _ORIENTATION
    -0.18
    foundland
    -0.18
    POSITIVE LOGITS
    ))==
    0.22
    ÑĤели
    0.21
    ikit
    0.21
    ORED
    0.21
    PointerException
    0.21
    uropean
    0.21
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.19
    ("")]↵
    0.19
    åľ¨è¿ĩ渡
    0.19
    ouston
    0.19
    Activations Density 0.001%

    No Known Activations