© 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. 16735
    Prev
    Next
    INDEX
    Explanations

    class, set, point, line

    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
    ajat
    -0.06
     (âĢŀ
    -0.06
     ("/
    -0.06
    uss
    -0.06
    jol
    -0.06
    ä½İä¸ĭ
    -0.06
     Jarvis
    -0.06
     Joc
    -0.06
    ãĥŀãĥģ
    -0.06
    cht
    -0.06
    POSITIVE LOGITS
    åľ°åĿĢä½įäºİ
    0.08
    EventArgs
    0.08
    çĤ¹åĦ¿
    0.07
    _locator
    0.07
    ®
    0.07
    å¢
    0.07
    ä¹ĭäºİ
    0.07
    "<<
    0.06
    apult
    0.06
    ä¹ĭæīĢ
    0.06
    Activations Density 0.003%

    No Known Activations