© 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. 20180
    Prev
    Next
    INDEX
    Explanations

    value and its impact

    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
    icamente
    -0.09
    aldi
    -0.08
    ahr
    -0.07
    ยัà¸ģษà¹Į
    -0.07
    严éĩįè¿Ŀæ³ķ
    -0.07
    ightly
    -0.07
    fertig
    -0.07
    uyer
    -0.07
    à¹ĥหà¸įà¹Ī
    -0.07
    allet
    -0.07
    POSITIVE LOGITS
    ä¸įèı²
    0.11
    -added
    0.10
    /value
    0.10
    -nil
    0.09
    fully
    0.09
    åĴĮä»·åĢ¼
    0.09
    uable
    0.09
    åĮªæµħ
    0.09
     proposition
    0.09
    è¿ŀåŁİ
    0.09
    Activations Density 0.040%

    No Known Activations