© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55844
    Prev
    Next
    INDEX
    Explanations

    Romanian names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¤ıå¨ģ夷
    -0.08
    ately
    -0.08
     Española
    -0.08
     اÙĦسعÙĪدÙĬ
    -0.08
     Informação
    -0.07
    åı¤å±ĭ
    -0.07
     Hawaiian
    -0.07
    attore
    -0.07
     Japanese
    -0.07
    alisierung
    -0.07
    POSITIVE LOGITS
     Romanian
    0.09
    éĥ´
    0.08
     Romania
    0.08
    escu
    0.08
    æ½ĩæ¹ĺ
    0.08
    æ¹ĺæ±Ł
    0.07
     Bucure
    0.07
    éĥ´å·ŀ
    0.07
    æ¹ĺ西
    0.07
     Biz
    0.07
    Activations Density 0.040%

    No Known Activations