© 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. 63773
    Prev
    Next
    INDEX
    Explanations

    code quotes and structures

    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
    æīĵä¸Ģ
    -0.06
    Âł
    -0.06
     '_',
    -0.06
    羸åŃIJ
    -0.06
     b
    -0.06
    zustellen
    -0.06
    cour
    -0.06
     _|
    -0.06
     @}
    -0.06
    мÑı
    -0.06
    POSITIVE LOGITS
    æľī以ä¸ĭ
    0.12
    åħ·æľī以ä¸ĭ
    0.12
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.11
    ä¸ĭè¿°
    0.10
     ëĭ¤ìĿĮê³¼
    0.09
    人以ä¸ĭ
    0.09
    以ä¸ĭãģ®
    0.09
    以ä¸ĭåĨħ容
    0.08
    以ä¸ĭåĩłä¸ª
    0.08
     ((((
    0.08
    Activations Density 0.750%

    No Known Activations