© 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. 21348
    Prev
    Next
    INDEX
    Explanations

    code and math symbols

    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
     ballo
    -0.08
    çī¹åĪ«å¤ļ
    -0.07
     terminal
    -0.07
    alo
    -0.07
    oo
    -0.07
    APTER
    -0.07
    pps
    -0.06
    ekar
    -0.06
     ():
    -0.06
    __:
    -0.06
    POSITIVE LOGITS
    åŁ¼
    0.07
    å°ijå¹´
    0.07
    -origin
    0.07
    å°ijå¹´çļĦ
    0.07
    çļĦå°ijå¹´
    0.07
    ä¸Ģä¹Ŀ
    0.07
    SharedPtr
    0.07
    PCS
    0.07
    ä¸Ģ两
    0.07
    ä¹ĿæĪIJ
    0.07
    Activations Density 0.001%

    No Known Activations