© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44064
    Prev
    Next
    INDEX
    Explanations

    relationship or association

    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
    aks
    -0.07
    æ±ĩ
    -0.06
    íļ¨
    -0.06
    æĺ¯æĿ¥èĩª
    -0.06
     meanwhile
    -0.06
    ä¸įæĺ¯æĪij
    -0.06
    西游
    -0.06
     extr
    -0.06
    ä¸įæ¯Ķ
    -0.06
    æĶ»
    -0.06
    POSITIVE LOGITS
     gắn
    0.09
    æľ¬èº«å°±æĺ¯
    0.09
    ä¸İä¹ĭ
    0.09
    åĤ¬çĶŁ
    0.08
     Relationship
    0.08
     association
    0.08
    _related
    0.08
    æĺ¯æݨåĬ¨
    0.08
    æݨåĬ¨ä½ľçĶ¨
    0.08
    çĽ¸ä¼´
    0.07
    Activations Density 0.298%

    No Known Activations