© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10728
    Prev
    Next
    INDEX
    Explanations

    what happens or what is

    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
    Âł
    -0.07
     mainly
    -0.07
     ensuing
    -0.07
     considerably
    -0.07
     (
    -0.06
    âĢIJ
    -0.06
     nevertheless
    -0.06
     nicely
    -0.06
    ↵
    -0.06
    '
    -0.06
    POSITIVE LOGITS
    æ¯ıä¸Ģ个åѦçĶŁ
    0.09
    igas
    0.09
    -solving
    0.09
    longleftrightarrow
    0.09
    åĬłè½½æĽ´å¤ļ
    0.09
    emergen
    0.09
    ä¸ŃåŃ¦ä¹ł
    0.09
    年建
    0.08
    etrize
    0.08
    ryo
    0.08
    Activations Density 0.019%

    No Known Activations