© 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. 12239
    Prev
    Next
    INDEX
    Explanations

    single sheet, single dependency, last counter

    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
    天ä¸Ģ
    -0.07
    ECT
    -0.07
    ŃIJ
    -0.07
    太åĴĮ
    -0.07
    ä¹ĭæĹħ
    -0.07
    ç±»ä¸ĵä¸ļ
    -0.07
     silen
    -0.07
    åıĮèħ¿
    -0.07
    anaan
    -0.07
    ÙĨ
    -0.06
    POSITIVE LOGITS
    able
    0.09
    aise
    0.08
    éĢ¼
    0.07
    icot
    0.07
    çħ§å¸¸
    0.07
    Bindable
    0.07
     discrete
    0.07
    ird
    0.07
    IRD
    0.07
    寸
    0.07
    Activations Density 0.041%

    No Known Activations