© 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. 45145
    Prev
    Next
    INDEX
    Explanations

    aim of study

    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
    धिà¤ķ
    -0.07
    æ¯ı天æľī
    -0.07
    asley
    -0.07
    ä¸įè¦ģåİ»
    -0.07
    该åĨħ容
    -0.07
    inkt
    -0.07
     ders
    -0.06
    éĺ¿ç±³
    -0.06
    ynd
    -0.06
    åºĶ该æĢİä¹Ī
    -0.06
    POSITIVE LOGITS
    æĹ¨åľ¨
    0.11
    ä¹ĭ缮çļĦ
    0.10
     aims
    0.10
     ÑĨелÑĮÑİ
    0.09
    çļĦ缮çļĦæĺ¯
    0.09
     aim
    0.09
     seeks
    0.09
    çļĦ缮çļĦ
    0.08
     purpose
    0.08
    寻æī¾
    0.08
    Activations Density 1.259%

    No Known Activations