© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59854
    Prev
    Next
    INDEX
    Explanations

    why is

    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
    Negative Logits
     اÙĨع
    -0.07
     validity
    -0.07
    çģ¿
    -0.07
    /null
    -0.07
    ç»Ĩå¾®
    -0.07
    Validity
    -0.07
    羡
    -0.07
    plast
    -0.07
     minister
    -0.07
    éľĸ
    -0.07
    POSITIVE LOGITS
     realistically
    0.07
    çļĦçİ°å®ŀ
    0.07
     worst
    0.07
    ä¸ĬéĻIJ
    0.07
    edor
    0.07
     Feliz
    0.07
    ä¿Ŀå®Ī
    0.07
    phis
    0.07
     manageable
    0.07
    åĪĨæķ£
    0.07
    Activations Density 0.023%

    No Known Activations