© 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. 47022
    Prev
    Next
    INDEX
    Explanations

    sqrt function

    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
    èĿĩ
    -0.09
    å½¹
    -0.07
     polit
    -0.07
    éĹŃå¡ŀ
    -0.07
    æĤĶ
    -0.07
    eward
    -0.07
    æĹłåģ¿
    -0.07
    éĹĨ
    -0.07
    uC
    -0.06
    ucks
    -0.06
    POSITIVE LOGITS
     sqrt
    0.16
    sqrt
    0.14
    _sqrt
    0.14
     squared
    0.13
    .Sqrt
    0.13
    å¹³æĸ¹
    0.13
    .sqrt
    0.13
     sqr
    0.11
    qrt
    0.11
     square
    0.11
    Activations Density 0.066%

    No Known Activations