© 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. 29506
    Prev
    Next
    INDEX
    Explanations

    least common multiple

    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
    ä½İå¼Ģ
    -0.08
    utton
    -0.07
    çĴŀ
    -0.07
    åħ¥å¾®
    -0.07
    coder
    -0.07
    èį¼
    -0.07
    åĽ¢éķ¿
    -0.07
    åĴĮæĦıä¹ī
    -0.07
    å¹´éĩĮ
    -0.07
    astica
    -0.07
    POSITIVE LOGITS
    åĢįæķ°
    0.08
    iliate
    0.08
     بÙĬÙĨÙĩا
    0.07
    åĮħ容
    0.07
    pron
    0.07
    ngen
    0.07
     Tre
    0.07
     MRT
    0.06
    åĽłä¸ºå®ĥ们
    0.06
    åĢį
    0.06
    Activations Density 0.006%

    No Known Activations