© 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. 1879
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
    PRINTF
    -0.22
    ä¿IJ
    -0.21
    zia
    -0.21
    ======
    -0.21
    SPORT
    -0.20
    éĥ¨åī¯
    -0.20
    .MouseDown
    -0.20
     .'</
    -0.20
    ieval
    -0.20
    åĭł
    -0.20
    POSITIVE LOGITS
    ate
    0.26
    atus
    0.26
    ated
    0.25
    ato
    0.25
    ates
    0.24
    ating
    0.23
    ateg
    0.23
    arel
    0.23
    ation
    0.22
    аÑĤелÑĮ
    0.21
    Activations Density 0.603%

    No Known Activations