© 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-CHAT-65K
    7. 46899
    Prev
    Next
    INDEX
    Explanations

    commonly

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    loquent
    -0.27
    -Trump
    -0.23
     {?>↵
    -0.23
    >:</
    -0.23
    incinn
    -0.23
    orgia
    -0.23
    irlines
    -0.23
    .uml
    -0.23
    cade
    -0.23
    ннаÑı
    -0.23
    POSITIVE LOGITS
     actionTypes
    0.22
    IMIZE
    0.19
    adius
    0.18
    еÑĩно
    0.18
    memory
    0.18
     etwa
    0.18
    using
    0.18
    ([]);↵
    0.18
    .LogWarning
    0.18
    .jsx
    0.17
    Activations Density 0.014%

    No Known Activations