© 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. 791
    Prev
    Next
    INDEX
    Explanations

    understand or explain concepts

    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
    åľ¨æŁIJäºĽ
    -0.09
     tiá»ģm
    -0.08
    æŁIJäºĽ
    -0.08
    æ½ľåľ¨çļĦ
    -0.07
    åIJĦç±»
    -0.07
    ghan
    -0.07
    èĢĥ究
    -0.07
    æľīéĴĪ对æĢ§åľ°
    -0.07
    æľ¬é¢ĺåĪĨæŀIJ
    -0.07
    åĪĨæŀIJæĬ¥åijĬ
    -0.07
    POSITIVE LOGITS
    åŁºæľ¬æ¦Ĥ念
    0.10
     explanation
    0.10
     concepts
    0.10
     обÑĬÑıÑģ
    0.10
    éĢļä¿Ĺ
    0.10
     explaining
    0.10
     expliqu
    0.09
     intuitive
    0.09
    缴è§Ĥ
    0.09
     Concepts
    0.09
    Activations Density 0.061%

    No Known Activations