© 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. 19631
    Prev
    Next
    INDEX
    Explanations

    give equations

    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
    eus
    -0.06
     discovery
    -0.05
     Discovery
    -0.05
    èį£
    -0.05
    åºĶå½ĵåľ¨
    -0.05
    afen
    -0.05
    /opt
    -0.05
     åb
    -0.05
    emukan
    -0.05
    åѦçĶŁå·¥ä½ľ
    -0.05
    POSITIVE LOGITS
    æ¨
    0.06
    untr
    0.06
    éĥ½è¡¨ç¤º
    0.05
     incond
    0.05
    å¾Ĺä½ı
    0.05
    rimon
    0.05
    itse
    0.05
    èĢĮä¸į
    0.05
    å¾Ĺä¸į
    0.05
    inkle
    0.05
    Activations Density 0.001%

    No Known Activations