© 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. 20064
    Prev
    Next
    INDEX
    Explanations

    national chess championship

    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
    ÑĤелÑĮ
    -0.06
    ao
    -0.05
    ae
    -0.05
    éĺ´
    -0.05
    åĴĮåİ¿
    -0.05
    å¤ĸéĢģ
    -0.05
     otherwise
    -0.05
    igh
    -0.05
    auce
    -0.05
    å·¥ä½ľçļĦåIJĮæŶ
    -0.05
    POSITIVE LOGITS
    å¾Īåı¯èĥ½æĺ¯
    0.06
    gestellt
    0.06
    lot
    0.05
     Domen
    0.05
    asuk
    0.05
    ç«
    0.05
     Äijá»Ļc
    0.05
     Alive
    0.05
    ç«ĭãģ¦
    0.05
    “At
    0.05
    Activations Density 0.005%

    No Known Activations