© 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. 55091
    Prev
    Next
    INDEX
    Explanations

    illegally parked / stopped

    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
    uckland
    -0.09
     herst
    -0.08
    ëģĪ
    -0.08
    ä¸İç»´ä¿®
    -0.08
    ÑģÑĤÑĢе
    -0.08
    åıĬéĶĢåĶ®
    -0.08
    rific
    -0.08
     Júnior
    -0.08
    çĤ¹åĩ»ä¸ĭè½½
    -0.08
    /loading
    -0.08
    POSITIVE LOGITS
    使çĶ¨åĴĮ
    0.10
    åŃ¦ä¹łåĴĮ
    0.08
    管çIJĨçŃī
    0.08
    å¤ĦçIJĨåĴĮ
    0.08
    æĢĿèĢĥåĴĮ
    0.08
    管çIJĨåĴĮ
    0.08
    è¿Ľè¡Į
    0.08
    å·¥ä½ľæĪĸ
    0.07
    åıijå±ķåĴĮ
    0.07
    åŃ¦ä¹łä¸İ
    0.07
    Activations Density 0.047%

    No Known Activations