© 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. 21821
    Prev
    Next
    INDEX
    Explanations

    symmetry and invariance

    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
     hipert
    -0.08
    éĿĻèĦīæĽ²å¼ł
    -0.07
    ureka
    -0.07
    çĿ¡ä¸įçĿĢ
    -0.07
     compareTo
    -0.07
    äºī缸
    -0.07
    Ñģмо
    -0.07
    çļĦé«ĺè´¨éĩı
    -0.07
     коло
    -0.07
     hypoc
    -0.07
    POSITIVE LOGITS
     upheld
    0.08
    éģµå®Ī
    0.08
    unde
    0.07
    ä¸įæ¸Ŀ
    0.07
     stringent
    0.07
    ä¸¥æł¼éģµå®Ī
    0.07
     chặt
    0.07
     strict
    0.07
     violations
    0.07
    ä¸¥æł¼çļĦ
    0.07
    Activations Density 0.002%

    No Known Activations