© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21966
    Prev
    Next
    INDEX
    Explanations

    class definitions and object creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
     минÑĥ
    -0.06
    imina
    -0.06
    èĥ½çļĦ
    -0.06
    ÙħÙĨت
    -0.05
    essa
    -0.05
    æĻĤåĢĻ
    -0.05
    parte
    -0.05
    paralle
    -0.05
     Born
    -0.05
    resse
    -0.05
    POSITIVE LOGITS
    ivers
    0.05
    ibil
    0.05
    /disable
    0.05
    EMAIL
    0.05
    ows
    0.05
    ivid
    0.05
    illard
    0.05
     obl
    0.05
    mit
    0.05
    {/
    0.05
    Activations Density 0.001%

    No Known Activations