© 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. 4249
    Prev
    Next
    INDEX
    Explanations

    statistical comparison

    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
    以人æ°ij为
    -0.19
    åĭł
    -0.18
     Institute
    -0.18
     isError
    -0.18
    STEM
    -0.18
    инÑĭ
    -0.18
     vej
    -0.18
     gridColumn
    -0.18
     ìľĦíķĺìŬ
    -0.17
    åIJĪä½ľåħ±èµ¢
    -0.17
    POSITIVE LOGITS
    riger
    0.24
    ;!
    0.24
    hipster
    0.23
     Mattis
    0.22
    lotte
    0.22
    erialized
    0.21
    itchen
    0.21
    rades
    0.21
    <=$
    0.21
    tfoot
    0.21
    Activations Density 0.004%

    No Known Activations