© 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. 25139
    Prev
    Next
    INDEX
    Explanations

    long distance

    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
    VENT
    -0.07
    æĸĩåĮĸ
    -0.07
    æ©ĺ
    -0.07
    æĸĩåĮĸåĴĮ
    -0.06
    çĬĢ
    -0.06
    æĬĬä½ł
    -0.06
    raje
    -0.06
    å§ĵ
    -0.06
    åĪ»
    -0.06
    vent
    -0.06
    POSITIVE LOGITS
    ä¸ĵäººè´Łè´£
    0.09
    æĢ»éĩı
    0.08
    è²¢
    0.08
    è¿Ļæĸ¹éĿ¢çļĦ
    0.07
    ä¸Ģç½ij
    0.07
    ä½ĵç³»
    0.07
    åľ¨è¿Ļæĸ¹éĿ¢
    0.07
     adequate
    0.07
    ä½ĵç³»çļĦ
    0.07
     Metropolitana
    0.07
    Activations Density 0.342%

    No Known Activations