© 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. 58176
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific terms

    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
     therefore
    -0.10
     однако
    -0.10
     however
    -0.10
    åĽłæŃ¤åľ¨
    -0.10
     donc
    -0.10
     wiÄĻc
    -0.09
    åĽłæѤ
    -0.09
     tehát
    -0.09
     обаÑĩе
    -0.08
    however
    -0.08
    POSITIVE LOGITS
    åĺĽ
    0.13
     przecież
    0.12
     appunto
    0.12
    çļĦç¼ĺæķħ
    0.12
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.10
    å®ŀåľ¨å¤ª
    0.09
    ç¼ĺæķħ
    0.09
     otherwise
    0.09
     altrimenti
    0.09
    å®ŀåľ¨æĺ¯å¤ª
    0.09
    Activations Density 0.324%

    No Known Activations