© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19405
    Prev
    Next
    INDEX
    Explanations

    most, greatest, best

    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
     of
    -0.08
     của
    -0.07
    ate
    -0.06
    ehl
    -0.05
    çĻ¾å·Ŀ
    -0.05
    çļĦåĨ³å®ļ
    -0.05
    аÑĤа
    -0.05
     schedule
    -0.05
     thereof
    -0.05
    ews
    -0.05
    POSITIVE LOGITS
     own
    0.06
    urkan
    0.06
    деÑĤÑĮÑģÑı
    0.06
    xes
    0.06
    ywa
    0.06
    å¾Ļ
    0.06
     stessi
    0.06
    ciera
    0.05
    æĽ´æĺ¯ä¸Ģ
    0.05
    [].
    0.05
    Activations Density 0.069%

    No Known Activations