© 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. 39659
    Prev
    Next
    INDEX
    Explanations

    traditional, hierarchy, sovereign

    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
    èī¯æĢ§
    -0.08
    éħĮ
    -0.08
    æ¯ĶæĻ®éĢļ
    -0.07
    ä¸ĿçļĦ
    -0.07
     genuinely
    -0.07
    ä»İ容
    -0.07
    éªļ
    -0.07
    ç¼ķ
    -0.07
    åĵ½
    -0.07
    ç¼Ń
    -0.07
    POSITIVE LOGITS
    çŃīä¼łç»Ł
    0.16
    çļĦä¼łç»Ł
    0.15
    ä¼łç»ŁçļĦ
    0.15
     traditional
    0.14
    ä¼łç»Ł
    0.13
     Traditional
    0.12
     tradicional
    0.12
    traditional
    0.12
    åĤ³çµ±çļĦ
    0.12
    Traditional
    0.12
    Activations Density 0.117%

    No Known Activations