© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10884
    Prev
    Next
    INDEX
    Explanations

    longitudinal spin

    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
    Äĩ
    -0.07
    zyd
    -0.07
    æĽľ
    -0.07
     bior
    -0.06
     Ø£ÙĪÙĦ
    -0.06
     assort
    -0.06
    ä¹ł
    -0.06
     bilingual
    -0.06
    æľŁ
    -0.06
    éļĶ
    -0.06
    POSITIVE LOGITS
    åľ¨åį³
    0.07
    è·¯ç«Ļ
    0.07
    udas
    0.07
    ä¸Ŀ
    0.07
     rightfully
    0.07
    à¹īม
    0.07
    uzzi
    0.07
     пÑĢово
    0.07
    ingo
    0.07
     thấu
    0.07
    Activations Density 0.001%

    No Known Activations