© 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. 63325
    Prev
    Next
    INDEX
    Explanations

    for example,

    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
     dafür
    -0.08
    人影
    -0.08
    对æѤ
    -0.07
    èĢħ为
    -0.07
    çļĦæł·åŃIJ
    -0.07
    å¯¹æľ¬æ¬¡
    -0.07
     für
    -0.07
     Uncategorized
    -0.07
    为æѤ
    -0.06
    à¤Ńि
    -0.06
    POSITIVE LOGITS
    èĢĮè¨Ģ
    0.13
    æĿ¥è¯´
    0.12
    人æĿ¥è¯´
    0.12
    çļĦ人æĿ¥è¯´
    0.10
    æĿ¥è¯´æĺ¯
    0.10
     purposes
    0.10
     geldt
    0.09
    ä¾Ĩ說
    0.09
    æĪijæĿ¥è¯´
    0.09
     sake
    0.08
    Activations Density 0.091%

    No Known Activations