© 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. 19004
    Prev
    Next
    INDEX
    Explanations

    list items

    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
    åħ¶åľ¨
    -0.09
    èĩªå·±åľ¨
    -0.08
    å®ĥåľ¨
    -0.07
    åľ¨äºĨ
    -0.07
    åľ¨æľ¬
    -0.07
    æľ¬äººåľ¨
    -0.07
    å±ĬæŶ
    -0.07
    åľ¨æ°´ä¸Ń
    -0.07
    åľ¨æľ¬æ¬¡
    -0.06
    åľ¨ç½ijä¸Ĭ
    -0.06
    POSITIVE LOGITS
    常说
    0.09
    ãģ£ãģįãĤĬ
    0.08
    ç»ı常åĩºçİ°
    0.08
    å¦Ĥæŀľä¸Ģ个
    0.08
    ä¸įä¹ı
    0.08
    ä¸įå¦ĤæĦı
    0.08
    çļĦä¸Ģ项éĩįè¦ģ
    0.07
    ç»ı常ä¼ļ
    0.07
    常æľī
    0.07
    uchos
    0.07
    Activations Density 0.081%

    No Known Activations