© 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. 50971
    Prev
    Next
    INDEX
    Explanations

    mechanical linkages and mechanisms

    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
     tent
    -0.08
    åŃ°
    -0.07
     Adler
    -0.07
     bund
    -0.06
     Tent
    -0.06
    涯
    -0.06
     extrav
    -0.06
    åıĹæįŁ
    -0.06
    Attempt
    -0.06
    é³ŀçīĩ
    -0.06
    POSITIVE LOGITS
    è¿ŀæĿĨ
    0.10
    åĩ¸è½®
    0.09
     hydraulic
    0.09
    åĽºå®ļè¿ŀæİ¥
    0.09
    ä¼¸çĽ´
    0.09
     crank
    0.08
    æĶ¯æī¿
    0.08
    ç½ijç«Ļ导èĪª
    0.08
     Hydraulic
    0.08
    åĽ¾çº¸
    0.08
    Activations Density 0.023%

    No Known Activations