© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61734
    Prev
    Next
    INDEX
    Explanations

    measure of extent

    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
    adari
    -0.08
    ä¸ĵ家æĮĩåĩº
    -0.07
    ä¸Ĭ使çĶ¨
    -0.07
     à¹ģย
    -0.07
    åľ°ä½¿çĶ¨
    -0.07
     никакиÑħ
    -0.07
    ÑĢоÑģÑģий
    -0.07
     begeist
    -0.07
    ä¸įæŀĦæĪIJ
    -0.07
    arefa
    -0.07
    POSITIVE LOGITS
    åıįæĺł
    0.09
    åıįæĺłäºĨ
    0.08
    æĢ»çļĦ
    0.08
     seberapa
    0.08
    è¡¡éĩı
    0.07
     reflecting
    0.07
     mewakili
    0.07
     extent
    0.07
     reflects
    0.07
     whether
    0.07
    Activations Density 0.040%

    No Known Activations