© 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. 33637
    Prev
    Next
    INDEX
    Explanations

    only organixation

    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
    ocup
    -0.08
     lieber
    -0.08
    æľ¬çīĩ
    -0.07
    æĭįæĭį
    -0.07
    æĽ´éĩįè¦ģçļĦ
    -0.07
     nonetheless
    -0.07
    é¼İé¼İ
    -0.07
    леб
    -0.07
    kast
    -0.07
     justamente
    -0.07
    POSITIVE LOGITS
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.11
     truly
    0.09
    羣æŃ£
    0.08
    undy
    0.07
     vraiment
    0.07
     viable
    0.07
    éĩı大
    0.07
    æľīè¿Ļä¹Ī
    0.07
     Truly
    0.07
    羣æŃ£çļĦ
    0.07
    Activations Density 0.147%

    No Known Activations