© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17584
    Prev
    Next
    INDEX
    Explanations

    native species or origins

    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
    iveau
    -0.07
    计
    -0.06
    неж
    -0.06
    ä¼´éļı
    -0.06
    åĴĮå¸Ĥ
    -0.06
     phÆ°á»Ŀng
    -0.06
    åĴĮåİ¿
    -0.05
    æĬķåħ¥
    -0.05
    ä¸Ģå±Ĥ
    -0.05
    èĬĤæĹ¥æľŁéĹ´
    -0.05
    POSITIVE LOGITS
    åĢĴæĺ¯
    0.06
     native
    0.05
     اÙĦأصÙĦÙĬ
    0.05
    é¦ĸ个
    0.05
     hina
    0.05
    ãĤĦãĤī
    0.05
    ony
    0.05
     aside
    0.05
    .native
    0.05
     sop
    0.05
    Activations Density 0.017%

    No Known Activations