© 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. 58228
    Prev
    Next
    INDEX
    Explanations

    topics at the end of sentences

    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
    åıªæĺ¯æĥ³
    -0.10
    çŃīä¼ĺçĤ¹
    -0.09
    posix
    -0.09
    acan
    -0.09
    åıªæĺ¯åľ¨
    -0.09
    åıªæĺ¯ä¸ºäºĨ
    -0.09
    æĥħåĨµåIJİ
    -0.09
    ادا
    -0.09
    çŃīä¼ĺåĬ¿
    -0.08
     ës
    -0.08
    POSITIVE LOGITS
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.14
    èĢĮå·²
    0.08
    åħ¶æ¬¡æĺ¯
    0.08
     itself
    0.08
    èĢĮéĿŀ
    0.08
     "".
    0.08
    åijĢ
    0.07
     rather
    0.07
    èĢĮè¿Ļ
    0.07
    èĢĮä¸įæĺ¯
    0.07
    Activations Density 0.668%

    No Known Activations