© 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. 847
    Prev
    Next
    INDEX
    Explanations

    asking for answers or solutions

    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
    osex
    -0.06
     mú
    -0.06
    åĢ¼å¾Ĺä¸ĢæıIJ
    -0.06
    个å°ı
    -0.06
    zte
    -0.06
     arguably
    -0.06
    implements
    -0.06
     Notice
    -0.06
    aset
    -0.06
    _STAGE
    -0.06
    POSITIVE LOGITS
    à¹Ģรà¹ĩวà¹Ĩ
    0.09
     möglichst
    0.09
     asap
    0.08
     ASAP
    0.08
    èĥ½æīĵ
    0.08
    æŁIJä¸Ģ天
    0.08
     urgently
    0.08
    èĥľè¿ĩ
    0.07
    +="
    0.07
    ä»ĸ们对
    0.07
    Activations Density 0.082%

    No Known Activations