© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1796
    Prev
    Next
    INDEX
    Explanations

    unusual words

    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
     Resorts
    -0.24
    /WebAPI
    -0.24
    .PropTypes
    -0.23
     IonicPage
    -0.22
    brtc
    -0.22
    æ¯Ļ
    -0.22
     ----------------------------------------------------------------------------------------------------------------
    -0.22
    @student
    -0.21
    relude
    -0.21
    ocurrency
    -0.21
    POSITIVE LOGITS
    forgettable
    0.24
     masturbating
    0.23
     subparagraph
    0.23
    dziaÅĤ
    0.23
    ï¼ĩ
    0.23
    åıĸåĨ³
    0.23
    /bower
    0.23
    å¾Īå¤ļæľĭåıĭ
    0.22
     Group
    0.22
    女æĢ§æľĭåıĭ
    0.22
    Activations Density 5.125%

    No Known Activations