© 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. 25186
    Prev
    Next
    INDEX
    Explanations

    username and password

    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
    éĩįè¦ģçļĦäºĭæĥħ
    -0.07
    ä¸īç±»
    -0.07
    è¿Ļä¸īç§į
    -0.06
    alt
    -0.06
    fin
    -0.06
    ä¸įäºĨäºĨ
    -0.06
    æīij
    -0.06
    (fin
    -0.06
    ç±»çŃī
    -0.06
    让对æĸ¹
    -0.06
    POSITIVE LOGITS
     lẫn
    0.10
    æľŁåĴĮ
    0.08
    åĴĮ
    0.08
    æĢ§åĴĮ
    0.08
     мен
    0.08
    éĺŁåĴĮ
    0.08
    ä¸İ
    0.08
    ancı
    0.07
    éĿ¢åĴĮ
    0.07
     à¤Ķर
    0.07
    Activations Density 0.204%

    No Known Activations