© 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. 15634
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with sin

    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
    æ¾Ħæ¸ħ
    -0.07
    åºı
    -0.07
    els
    -0.07
    åį¿
    -0.06
    æıŃå¼Ģ
    -0.06
    åīįæľŁçļĦ
    -0.06
    nea
    -0.06
    urado
    -0.06
     Pr
    -0.06
    laus
    -0.06
    POSITIVE LOGITS
    åĨĴ
    0.08
    olg
    0.07
    ç»Ŀ伦
    0.07
    occo
    0.07
    ryn
    0.07
     jud
    0.07
     Dalle
    0.07
    зина
    0.07
    ogr
    0.07
    atement
    0.07
    Activations Density 0.014%

    No Known Activations