© 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. 20927
    Prev
    Next
    INDEX
    Explanations

    mathematical 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
    å¨ħ
    -0.08
    odo
    -0.07
    å¥ĩ
    -0.07
    kow
    -0.07
    Cong
    -0.06
     دستÙĪر
    -0.06
    _BOOT
    -0.06
    é¢Į
    -0.06
    æ³¥
    -0.06
    ys
    -0.06
    POSITIVE LOGITS
    swire
    0.08
    nees
    0.07
    ogle
    0.07
    posix
    0.07
    仲è£ģå§Ķåijĺä¼ļ
    0.07
    angsa
    0.07
    weeted
    0.07
     Ving
    0.07
    Ùĥا
    0.07
    é¦ĻçļĦ
    0.07
    Activations Density 0.002%

    No Known Activations