© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52215
    Prev
    Next
    INDEX
    Explanations

    So, both, what

    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
    Negative Logits
    zada
    -0.08
    oute
    -0.07
    igm
    -0.07
     Sometimes
    -0.07
    å¤įæĿĤ
    -0.07
    anche
    -0.07
    æŀ¶ä¸Ĭ
    -0.07
    ä¹Łç®Ĺ
    -0.06
    ä»įéľĢ
    -0.06
    aufnahme
    -0.06
    POSITIVE LOGITS
    town
    0.08
    ä½İå¼Ģ
    0.07
    ä¸įè¨ĢèĢĮåĸ»
    0.07
    ç»ĵæŀľæĺ¯
    0.06
    åľ¨å¾Ī大ç¨ĭ度ä¸Ĭ
    0.06
    èĩªçĦ¶æĺ¯
    0.06
    è¯ŃéŁ³æŶéķ¿
    0.06
    tet
    0.06
    举ä¸ĸ
    0.06
    æį
    0.06
    Activations Density 0.002%

    No Known Activations