© 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. 38667
    Prev
    Next
    INDEX
    Explanations

    radius, near, distance

    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
    çİĩé«ĺ
    -0.07
    ding
    -0.07
    ä¸įæģ¯
    -0.06
     mat
    -0.06
     argv
    -0.06
     remar
    -0.06
    çİĩçļĦ
    -0.06
    æ´ĹçīĮ
    -0.06
    çİĩ为
    -0.06
     tent
    -0.06
    POSITIVE LOGITS
    åįĬå¾Ħ
    0.08
    ibir
    0.08
    å¤ĸåŀĭ
    0.08
    大红
    0.08
    æ¼ı
    0.07
     exterior
    0.07
    å¿Ĺ
    0.07
    ExceptionHandler
    0.07
    -radius
    0.07
    غÙĨ
    0.07
    Activations Density 0.001%

    No Known Activations