© 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. 64335
    Prev
    Next
    INDEX
    Explanations

    bleach-fixing processing

    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
    ç°¸
    -0.07
    /runtime
    -0.07
    kok
    -0.07
    åĪ¶ä½ľçļĦ
    -0.07
    åĬį
    -0.06
    çļĦåĽłç´ł
    -0.06
    опо
    -0.06
    åºĹéĩĮ
    -0.06
    à¸ŀิม
    -0.06
    isar
    -0.06
    POSITIVE LOGITS
    åīįè¿°
    0.09
     appunto
    0.08
    å¦Ĥä¸Ĭ
    0.08
    inka
    0.07
     aforementioned
    0.07
    æ£ł
    0.07
    ä¸Ĭè¿°
    0.07
    Above
    0.07
    ä¸ĬéĿ¢çļĦ
    0.07
     inde
    0.07
    Activations Density 0.030%

    No Known Activations