© 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. 27729
    Prev
    Next
    INDEX
    Explanations

    demonstrate or test

    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
    jaman
    -0.09
    _pdata
    -0.08
    ä»»ä½ķä¿Ŀè¯ģ
    -0.08
    ovol
    -0.08
    æĭ³éģĵ
    -0.08
     ì¦Ŀê±°
    -0.08
    ίαÏĤ
    -0.07
    èĩªè¾¾
    -0.07
    ç¼Ī
    -0.07
    å¾ĹçĽĬ
    -0.07
    POSITIVE LOGITS
    åѦçĶŁå¯¹
    0.10
    åŁºæľ¬çŁ¥è¯Ĩ
    0.10
     knowledge
    0.10
    çŁ¥è¯Ĩ
    0.08
     знание
    0.08
    åŁºç¡ĢçŁ¥è¯Ĩ
    0.08
     grasp
    0.08
    knowledge
    0.08
     Knowledge
    0.07
     understanding
    0.07
    Activations Density 0.009%

    No Known Activations