© 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. 14889
    Prev
    Next
    INDEX
    Explanations

    etiology

    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
    ä¸īçıŃ
    -0.07
    éĢĤ
    -0.07
     geri
    -0.07
     ìĭĿ
    -0.07
    IDX
    -0.06
    åĸľæĤ¦
    -0.06
    ä¸īé¤IJ
    -0.06
    TypeID
    -0.06
    ¿
    -0.06
    gam
    -0.06
    POSITIVE LOGITS
    ä¹ĭè°ľ
    0.11
    ä¼¼ä¹İæĺ¯
    0.10
    ä¼¼ä¹İ
    0.10
    çłĶ究表æĺİ
    0.09
    åĪ°åºķæĺ¯
    0.09
     theories
    0.09
     research
    0.09
     mysterious
    0.09
     correlates
    0.09
    好åĥıæĺ¯
    0.09
    Activations Density 1.507%

    No Known Activations