© 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. 14502
    Prev
    Next
    INDEX
    Explanations

    Higgs bosons, scalar, care act

    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
    _MAKE
    -0.08
     domicili
    -0.08
    portes
    -0.08
    çĴĢ
    -0.08
    éĵ®
    -0.07
    çĿĢ头
    -0.07
    å·¥æķ´
    -0.07
     záp
    -0.07
    åĪ©çĶ¨ãģ§ãģįãĤĭ
    -0.07
    SCII
    -0.07
    POSITIVE LOGITS
    bos
    0.08
     bos
    0.08
    ç²
    0.08
    etin
    0.07
     quadr
    0.07
    medi
    0.07
     Cele
    0.07
     клÑİ
    0.06
    ä¹³æĪ¿
    0.06
    ella
    0.06
    Activations Density 0.012%

    No Known Activations