© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3995
    Prev
    Next
    INDEX
    Explanations

    winning medals

    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
     NDEBUG
    -0.22
    -pill
    -0.22
    éĢīåĩº
    -0.20
    /Foundation
    -0.20
    ltre
    -0.20
     Inquiry
    -0.20
    åIJįåĪĹåīį
    -0.19
    ä»ħ次
    -0.19
    swers
    -0.19
    _LOGGER
    -0.19
    POSITIVE LOGITS
    èĥľåĪ©
    0.24
    æ±Ĩ
    0.24
    å®Ŀè´µ
    0.21
    ï¿¡
    0.21
    å°±ä¸ļå²Ĺä½į
    0.20
     victory
    0.20
    åľ°ä½į
    0.20
    mercial
    0.20
    åįļ士åѦä½į
    0.20
    TOTYPE
    0.19
    Activations Density 0.428%

    No Known Activations