© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 817
    Prev
    Next
    INDEX
    Explanations

    Standard Model

    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
    ÙĨÛĮÙĨ
    -0.08
    nage
    -0.08
    usc
    -0.08
    Ñħол
    -0.07
     Mondi
    -0.07
    ertext
    -0.07
    Ợ
    -0.07
    æľ¨èĢ³
    -0.07
    اÛģ
    -0.07
     Mange
    -0.07
    POSITIVE LOGITS
    -era
    0.08
     baseline
    0.06
    anty
    0.06
    åĴĮæľªæĿ¥
    0.06
    orge
    0.06
    Ø«ÙĨ
    0.06
    ÑģÑĤÑıми
    0.06
    ployment
    0.06
    -model
    0.06
    lich
    0.06
    Activations Density 0.013%

    No Known Activations