© 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. 3588
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts involving sets, spaces, or indices

    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
    é¦Ī
    -0.08
     operand
    -0.07
    æĸ°å±Ģ
    -0.07
    ä¾ĽåºĶ产åĵģ
    -0.07
    plate
    -0.07
    adena
    -0.07
    igio
    -0.07
    watan
    -0.07
    è¿ĶåĽŀ顶éĥ¨
    -0.07
    Manip
    -0.07
    POSITIVE LOGITS
    amanan
    0.07
     discret
    0.07
    æķ°éĩıæľīéĻIJ
    0.07
    Mult
    0.07
    vaj
    0.07
    ä¸įåĪ°çļĦ
    0.07
    åįģæĿ¡
    0.06
    失
    0.06
    cim
    0.06
    _approx
    0.06
    Activations Density 0.006%

    No Known Activations