© 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. 28081
    Prev
    Next
    INDEX
    Explanations

    either or except

    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
    ä¸ĢçĽ´æ²¡æľī
    -0.10
    æķ´ä¸ªéĹ®é¢ĺ
    -0.09
    æīĢæľīåĨħ容
    -0.09
    æķ´ä¸ªè¿ĩç¨ĭ
    -0.09
    ashi
    -0.09
    æķ´åĢĭ
    -0.08
    äºĨå¾Īå¤ļ
    -0.08
    å¾Īå¤ļåľ°æĸ¹
    -0.08
     ìŀIJ주
    -0.08
    æĺ¯æķ´ä¸ª
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļæĪĸå°ij
    0.12
     تÙĤرÙĬب
    0.11
     either
    0.10
    è¦ģä¹Ī
    0.10
    ä¸įåIJĮç¨ĭ度
    0.10
     except
    0.09
    —including
    0.09
    except
    0.08
    è¦ģä¹Īæĺ¯
    0.08
    缴æİ¥æĪĸéĹ´æİ¥
    0.08
    Activations Density 0.064%

    No Known Activations