© 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. 20235
    Prev
    Next
    INDEX
    Explanations

    efficient multiple

    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
    ÙĪغ
    -0.07
    portes
    -0.06
    åĮĪ
    -0.06
    ãģ¤ãģĦãģ¦
    -0.06
     .**
    -0.06
    æ²Ľ
    -0.06
    vog
    -0.06
    cott
    -0.06
    ivate
    -0.06
    ettem
    -0.06
    POSITIVE LOGITS
    зи
    0.05
    eng
    0.05
    ÙİرÙİ
    0.05
    meister
    0.05
    дÑĭн
    0.05
    æľ¬ä¼ģä¸ļ
    0.05
     اÙĦÙĥت
    0.04
    å¼Ģå°ģ
    0.04
    abl
    0.04
     riches
    0.04
    Activations Density 0.315%

    No Known Activations