© 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. 20406
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or statistics

    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
    ooth
    -0.06
    ä½¼
    -0.06
    éģĵéķ¿
    -0.06
    вл
    -0.06
    ISCO
    -0.06
    éĢ»
    -0.05
     preoc
    -0.05
    seh
    -0.05
    ãĥ¼ãĤ«ãĥ¼
    -0.05
    WithDuration
    -0.05
    POSITIVE LOGITS
    abb
    0.05
    ä¸įå½Ĵ
    0.05
     guidelines
    0.05
    ÑĢай
    0.05
    èĩ
    0.05
     зад
    0.05
    奧
    0.05
     po
    0.05
    ings
    0.05
    ема
    0.05
    Activations Density 0.016%

    No Known Activations