© 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. 56170
    Prev
    Next
    INDEX
    Explanations

    transfer/segregate/load

    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
    ongan
    -0.08
    è¿ĶåĽŀåĪĹ表
    -0.07
    缺ä¹ı
    -0.07
    ãĥ¢ãĥģ
    -0.07
    opus
    -0.07
    æ®Ĭ
    -0.07
     Reyn
    -0.07
    estre
    -0.07
    imid
    -0.07
    ÑĪÑĮÑģÑı
    -0.07
    POSITIVE LOGITS
    ä¸įä¼ļå½±åĵį
    0.13
    ä¸įå½±åĵį
    0.13
     isol
    0.10
    åĪĨéĽ¢
    0.10
     sacr
    0.10
    éļĶ离
    0.09
    isol
    0.09
     expend
    0.09
    çīºçī²
    0.09
    æī¿æĭħçļĦ
    0.09
    Activations Density 0.156%

    No Known Activations