© 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. 24460
    Prev
    Next
    INDEX
    Explanations

    English language contexts

    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
    isman
    -0.07
    нÑıка
    -0.07
     Hint
    -0.07
    baum
    -0.07
     irres
    -0.07
    æ¯ĶæĻ®éĢļ
    -0.07
     porr
    -0.07
    гда
    -0.07
    emps
    -0.07
    ç¼ĸè¾ijæݨèįIJ
    -0.06
    POSITIVE LOGITS
    åıĮè¯Ń
    0.07
     bilingual
    0.07
    amore
    0.07
    æĸ¹ä¾¿
    0.07
    ASS
    0.07
     lingua
    0.07
    .deb
    0.07
    Pid
    0.07
    åĭī
    0.07
    夹æĿĤ
    0.07
    Activations Density 0.013%

    No Known Activations