© 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. 12257
    Prev
    Next
    INDEX
    Explanations

    operators of the Poincaré Group

    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
     tráng
    -0.09
    anzi
    -0.07
    ä¸įæģ¯
    -0.07
    åĨįè§ģ
    -0.07
    家åºĦ
    -0.07
    ä»İ天èĢĮéĻį
    -0.07
    ewe
    -0.07
    städ
    -0.07
    åºĦéķĩ
    -0.06
    ogo
    -0.06
    POSITIVE LOGITS
    calar
    0.08
    ioxide
    0.07
    Race
    0.06
    LastError
    0.06
    ä¹Ŀä¹Ŀ
    0.06
     imprint
    0.06
    outdir
    0.06
    aura
    0.06
    大佬
    0.06
    alloc
    0.06
    Activations Density 0.001%

    No Known Activations