© 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. 48025
    Prev
    Next
    INDEX
    Explanations

    authenticating former historical periods

    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
    ´Ī
    -0.09
    riture
    -0.08
     ePub
    -0.08
    æīĢæĢĿ
    -0.08
    çĴĭ
    -0.08
     abw
    -0.08
    ç»ıèIJ¥é¡¹çĽ®
    -0.08
    ppers
    -0.08
    tribu
    -0.08
    adem
    -0.07
    POSITIVE LOGITS
     famously
    0.10
    ä¸ĩå²ģ
    0.08
    被èªī为
    0.07
    èijĹåIJįçļĦ
    0.07
     famous
    0.07
    á
    0.06
     controversial
    0.06
     paradox
    0.06
    antin
    0.06
    好åĥıæĺ¯
    0.06
    Activations Density 1.652%

    No Known Activations