© 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. 19853
    Prev
    Next
    INDEX
    Explanations

    tables and lists

    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
     phenomenon
    -0.06
    å¼ĢåıijåĮº
    -0.06
    buster
    -0.06
    à¸łà¸²à¸ŀ
    -0.06
     phenomena
    -0.05
    ois
    -0.05
    åį·
    -0.05
    оÑģÑĤÑĮÑİ
    -0.05
    饱
    -0.05
    çĦ¶
    -0.05
    POSITIVE LOGITS
    大äºĭ
    0.06
    olds
    0.05
    odings
    0.05
    éĩįè¦ģçļĦäºĭæĥħ
    0.05
    éģķãģĦãģ¾ãģĻ
    0.05
    èĥ³
    0.05
     répart
    0.05
    ä¸įåIJĮ
    0.05
    ä¸įåIJĮç±»åŀĭ
    0.05
    åľ°è¡¨
    0.05
    Activations Density 0.108%

    No Known Activations