© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22787
    Prev
    Next
    INDEX
    Explanations

    I replied

    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
    ä¸ĭåIJĮ
    -0.07
    æŶæīĢ
    -0.06
    缴æİ¥æĪĸéĹ´æİ¥
    -0.06
    æĪijè¦ģæĬķè¯ī
    -0.06
    åıªæĢķ
    -0.06
    reif
    -0.06
    æģ©æĸ¯
    -0.06
     rushing
    -0.06
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.06
     mas
    -0.06
    POSITIVE LOGITS
    以ä¸Ģ个
    0.07
    示æĦı
    0.07
     باÙĦطبع
    0.07
    _DECLS
    0.07
    uml
    0.07
    æľīäºĽ
    0.07
    antos
    0.07
    鼶è·Ŀ离
    0.07
    sos
    0.07
    oret
    0.07
    Activations Density 0.065%

    No Known Activations