© 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. 48077
    Prev
    Next
    INDEX
    Explanations

    buying, rheumatoid arthritis, dysfunction, urbanization, applications, loss

    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
     bersangkutan
    -0.08
    åIJİèĢħ
    -0.08
    .wik
    -0.07
    ä¸ŃäºĨ
    -0.07
    åºĶæľīçļĦ
    -0.07
     eher
    -0.07
     ÑıкобÑĭ
    -0.07
     (?)
    -0.07
    isode
    -0.07
    aunch
    -0.07
    POSITIVE LOGITS
    ä¹ĭæīĢ以
    0.10
    çłĶ究表æĺİ
    0.08
     tehát
    0.08
    ãģ«éĻIJ
    0.08
    æĥħåĨµåĪĨæŀIJ
    0.08
     indeed
    0.07
    odore
    0.07
     λοι
    0.07
    æĺ¯äººä»¬
    0.07
    æĺ¯ä¸Ģ个éĿŀ常
    0.07
    Activations Density 0.265%

    No Known Activations