© 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. 31485
    Prev
    Next
    INDEX
    Explanations

    function arguments or definitions

    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
    çļĦçĶŁåij½
    -0.07
    å¼łå¿Ĺ
    -0.07
    ä¼°
    -0.07
    漪
    -0.07
    ä¹ī
    -0.07
    FieldValue
    -0.06
    çīĩçīĩ
    -0.06
    езде
    -0.06
     Richt
    -0.06
    onda
    -0.06
    POSITIVE LOGITS
    è°ģæĺ¯
    0.08
     подобÑĢ
    0.08
     dum
    0.07
    ARGV
    0.07
    缸åħ³æݨèįIJ
    0.07
    args
    0.07
     argc
    0.07
     оÑģмо
    0.07
    anic
    0.07
    mel
    0.07
    Activations Density 0.009%

    No Known Activations