© 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. 43080
    Prev
    Next
    INDEX
    Explanations

    is designedis generallyis madeis roughlyis grown

    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
    æľīæĿ¡ä»¶
    -0.08
    sis
    -0.08
    cier
    -0.08
    éĵ¿
    -0.07
    lessness
    -0.07
    lements
    -0.07
     ê·¸ëĵ¤ìĿĢ
    -0.07
    bing
    -0.07
    亿åħĥçļĦ
    -0.07
     ìĿ´ìłľëĬĶ
    -0.07
    POSITIVE LOGITS
    nt
    0.09
     usually
    0.09
     indeed
    0.08
    ãģ¨ãģĦãģĨãģ¨
    0.08
    sembl
    0.08
     typically
    0.08
     often
    0.07
    semble
    0.07
     infatti
    0.07
     itself
    0.07
    Activations Density 0.004%

    No Known Activations