© 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. 50431
    Prev
    Next
    INDEX
    Explanations

    math expressions with sqrt

    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
    é¾Ħ
    -0.07
    enta
    -0.07
     Hag
    -0.07
     pert
    -0.07
    entar
    -0.07
    è¦ģæ±Ĥèĩªå·±
    -0.07
    积æŀģæĬķ身
    -0.07
    åĪĩå®ŀåģļåĪ°
    -0.07
    è´¨
    -0.07
    olut
    -0.07
    POSITIVE LOGITS
    æĭīå¾·
    0.07
    ä¸Ńç«ĭ
    0.07
    amed
    0.07
    ÙĪرش
    0.07
    iders
    0.07
    RECT
    0.07
    ARGIN
    0.07
    ä¸ŃæĢ§
    0.07
    åĵª
    0.06
    .receiver
    0.06
    Activations Density 0.042%

    No Known Activations