© 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. 10447
    Prev
    Next
    INDEX
    Explanations

    special characters and Chinese text

    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
     "***
    -0.09
    潺
    -0.08
     "[
    -0.07
    客
    -0.07
    çĴIJ
    -0.07
    éĢĶ
    -0.07
    lada
    -0.07
    /***
    -0.07
    ellet
    -0.07
    ×ķר×Ķ
    -0.07
    POSITIVE LOGITS
    âĢij
    0.08
    æľ¬åľºæ¯ĶèµĽ
    0.07
     âĢ¦
    0.07
     (âĢ¦)
    0.07
    æľ¬åĬŀæ³ķ
    0.07
    ‘
    0.07
     ‘
    0.06
     Wolfsburg
    0.06
    æľ¬æ³ķ
    0.06
    [,]
    0.06
    Activations Density 0.028%

    No Known Activations