© 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. 12730
    Prev
    Next
    INDEX
    Explanations

    still followed by contrasts or continuation

    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
     also
    -0.10
     indeed
    -0.09
    also
    -0.08
    æŃ£å¥½
    -0.08
    ä¹ŁæŃ£æĺ¯
    -0.08
     ÑĤакже
    -0.08
    åIJĮæĹ¶ä¹Ł
    -0.08
     likewise
    -0.08
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.07
    úl
    -0.07
    POSITIVE LOGITS
     ìŬìłĦíŀĪ
    0.13
    ä»įéľĢ
    0.13
    çħ§æł·
    0.12
    æĪij们è¿ĺæĺ¯
    0.12
     ë¶Ī구íķĺê³ł
    0.11
    è¿ĺæĺ¯éľĢè¦ģ
    0.11
    ä»įå°Ĩ
    0.11
    éĤ£åı¥è¯Ŀ
    0.11
    è¿ĺæĺ¯æľīäºĽ
    0.10
    è¿ĺæĺ¯ä¼ļ
    0.10
    Activations Density 0.189%

    No Known Activations