© 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. 8994
    Prev
    Next
    INDEX
    Explanations

    that is why

    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
    æľīçĤ¹åĥı
    -0.08
    æľīçĤ¹
    -0.07
     Ø£ÙİØŃ
    -0.07
     ÚĨÙĩ
    -0.07
    èģĶéĺ²
    -0.06
    ocache
    -0.06
    缴æİ¥æĪĸéĹ´æİ¥
    -0.06
    {}.
    -0.06
    ả
    -0.06
    以åıĬä¸İ
    -0.06
    POSITIVE LOGITS
    è¿Ļåıªæĺ¯
    0.08
    .central
    0.07
    çĸı
    0.07
    acles
    0.07
     oversight
    0.07
    agues
    0.07
     rectific
    0.07
    åıªæĺ¯ä¸ª
    0.07
    æĭį
    0.07
    åıªæĺ¯ä¸Ģ
    0.07
    Activations Density 0.049%

    No Known Activations