© 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. 2166
    Prev
    Next
    INDEX
    Explanations

    listing license information

    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
    æľĢç»Ī
    -0.07
     Final
    -0.07
    åIJĪ
    -0.06
    èĪ
    -0.06
     fatally
    -0.06
    Final
    -0.06
    ç¦ģ
    -0.06
    ä¸ī大
    -0.06
    mates
    -0.06
    oret
    -0.06
    POSITIVE LOGITS
    ë§Īëĭ¤
    0.13
    åľ¨æ¯ı个
    0.11
    æ¯ıæ¯ı
    0.10
    æ¯ı次éĥ½
    0.10
    æ¯ıé¢ĺ
    0.10
     ëķĮë§Īëĭ¤
    0.10
    à¹ĥà¸Ļà¹ģà¸ķà¹Īละ
    0.10
     each
    0.10
     каждое
    0.10
    æĺ¯æ¯ı个
    0.09
    Activations Density 0.009%

    No Known Activations