© 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. 27928
    Prev
    Next
    INDEX
    Explanations

    remainder when X is divided by Y

    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
    kler
    -0.09
    _pins
    -0.08
    Senin
    -0.08
    Dim
    -0.08
    gat
    -0.08
    eldo
    -0.08
    çľģå§Ķ常å§Ķ
    -0.07
    æĹ¥åİĨ天
    -0.07
    DECL
    -0.07
     Dim
    -0.07
    POSITIVE LOGITS
     juz
    0.09
    abit
    0.07
    resto
    0.06
    åĪ¤å®ļ
    0.06
     Whole
    0.06
    pons
    0.06
    çIJħ
    0.06
    æķ´
    0.06
    _ACCEPT
    0.06
    avant
    0.06
    Activations Density 0.006%

    No Known Activations