© 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
    2. Qwen2.5-7B-IT
    3. 20-MATRYOSHKA-65K
    4. 4170
    Prev
    Next
    INDEX
    Explanations

    code and special characters

    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
    Negative Logits
    ono
    -0.22
    v
    -0.20
    æĿijéķĩ
    -0.19
    åĽ½ç±į
    -0.19
    åĢº
    -0.19
     bond
    -0.19
    structors
    -0.18
    æİ³
    -0.18
    触
    -0.18
    被æī§è¡Į
    -0.18
    POSITIVE LOGITS
     fkk
    0.25
     }}>{
    0.23
    åľ¨çݩ家ä¸Ń
    0.23
    )))));↵
    0.23
    &&!
    0.22
    è¯Ĵ
    0.21
    .');
    0.21
    ');?>↵
    0.21
    -Jul
    0.21
    __);
    0.20
    Activations Density 0.002%

    No Known Activations