© 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. 3347
    Prev
    Next
    INDEX
    Explanations

    second, third, 2, year

    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
     final
    -0.08
    æľĢåIJİçļĦ
    -0.08
    æľĢç»ĪçļĦ
    -0.08
    æľĢç»Ī以
    -0.08
     Final
    -0.08
    æľĢåIJİæĺ¯
    -0.08
     ultima
    -0.08
    .final
    -0.07
    æľĢç»Ī
    -0.07
    æľĢåIJİåľ¨
    -0.07
    POSITIVE LOGITS
    ä¹ĭåIJİçļĦ
    0.10
    以åIJİçļĦ
    0.09
    æĹ¥åIJİçļĦ
    0.09
    æİ¥çĿĢ
    0.09
    å¾ĢåIJİ
    0.09
    æİ¥ä¸ĭæĿ¥çļĦ
    0.08
    ä¹ĭåIJİå°±
    0.08
    åľ¨ä»¥åIJİ
    0.08
    next
    0.08
    ç´§æİ¥çĿĢ
    0.08
    Activations Density 0.189%

    No Known Activations