© 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. 51943
    Prev
    Next
    INDEX
    Explanations

    digits follow numbers

    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
    æĪĸéĥ¨åĪĨ
    -0.08
    Interpreter
    -0.08
    adel
    -0.08
     Barcl
    -0.08
    çµķå°į
    -0.08
    _|
    -0.08
    ì§ģ
    -0.08
    دÙĦ
    -0.08
     \/
    -0.07
     vét
    -0.07
    POSITIVE LOGITS
    éľĨ
    0.07
    ari
    0.06
    à¹Ĥส
    0.06
    âij
    0.06
    ese
    0.06
    åı¦ä¸Ģæĸ¹éĿ¢
    0.06
    èĢĮåĿIJ
    0.06
    èĪĴ
    0.06
    å·¥åħ·åĴĮ
    0.06
    à¹Ĥà¸ŀ
    0.05
    Activations Density 0.035%

    No Known Activations