© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58775
    Prev
    Next
    INDEX
    Explanations

    parts of US locations

    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
    .inverse
    -0.08
    ä½Ļ
    -0.08
    arr
    -0.08
    วà¸Ļ
    -0.07
     nghá»ĭch
    -0.07
    ogue
    -0.07
    æľīä½Ļ
    -0.07
    inä
    -0.07
    æľīéĤ£ä¹Ī
    -0.07
    +xml
    -0.07
    POSITIVE LOGITS
    à¹Ģลย
    0.09
    åħ¨éĥ¨çļĦ
    0.07
     completos
    0.07
     Samar
    0.07
    æīĢæľīçļĦ人
    0.07
    åħ¨éĿ¢çļĦ
    0.07
    ered
    0.07
    åħ¨æĸ¹ä½įçļĦ
    0.07
    éĥ½éĿŀ常
    0.07
    å®Įæķ´çļĦ
    0.07
    Activations Density 0.467%

    No Known Activations