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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19458
    Prev
    Next
    INDEX
    Explanations

    grab / grabbed

    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
    ys
    -0.08
    uais
    -0.07
    eno
    -0.06
    çļĦ
    -0.06
    ê¾¼
    -0.06
    uum
    -0.06
    ua
    -0.05
    óta
    -0.05
    è´¨çļĦ
    -0.05
    æīĭæı¡
    -0.05
    POSITIVE LOGITS
    ative
    0.07
    ست
    0.07
    ÙĬÙĨ
    0.06
    arget
    0.06
     же
    0.06
    ford
    0.06
    sert
    0.06
    å¤ļãģĦãģ§ãģĻ
    0.06
    onis
    0.06
    umber
    0.06
    Activations Density 0.002%

    No Known Activations