© 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. 24323
    Prev
    Next
    INDEX
    Explanations

    `č` followed by words or `Bulgaria`

    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
    icont
    -0.08
    ä¾ĭå¦Ĥ
    -0.08
    uze
    -0.08
    çļĦåĩłä¸ª
    -0.07
    oucher
    -0.07
    °
    -0.07
    ighted
    -0.07
    åĪ©æ°ij
    -0.07
    å¤ļä¸ĩåħĥ
    -0.07
    igh
    -0.07
    POSITIVE LOGITS
    ulte
    0.07
    å®īåIJī
    0.07
     Apprentice
    0.07
     joys
    0.07
    allas
    0.07
    说åIJ§
    0.07
    æīĭåĨĮ
    0.07
    -minded
    0.06
    é²į
    0.06
    ä¸Ģæľ¬ä¹¦
    0.06
    Activations Density 0.059%

    No Known Activations