© 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. 11314
    Prev
    Next
    INDEX
    Explanations

    hydrogen or H-based spectroscopy

    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
    Ñģнов
    -0.08
     Ñģоли
    -0.08
    ros
    -0.07
    对åħļ
    -0.07
    端åĢª
    -0.07
    åĽºéĨĩ
    -0.07
    çĹħæŃ»
    -0.07
    ools
    -0.07
    queen
    -0.07
    æľ¬æ¡Ī
    -0.07
    POSITIVE LOGITS
     pico
    0.07
    åįij
    0.07
    å°ıåŃIJ
    0.07
     Hydro
    0.06
    çݲ
    0.06
    马éĩĮ
    0.06
    erland
    0.06
    idd
    0.06
    æ´ģåĩĢ
    0.06
    åŁİå¤ĸ
    0.06
    Activations Density 0.005%

    No Known Activations