© 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. 40670
    Prev
    Next
    INDEX
    Explanations

    labeling content types

    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
    Indented
    -0.08
    /helper
    -0.08
    ehme
    -0.07
     ảo
    -0.07
    èįŁ
    -0.07
    chooser
    -0.07
     unsus
    -0.07
    ηÏĤ
    -0.07
     divid
    -0.07
     desemp
    -0.07
    POSITIVE LOGITS
    ï¼ļ“
    0.07
    สัม
    0.07
    èĵ
    0.07
    :
    0.07
     suggests
    0.07
    åIJ«ä¹ī
    0.07
     "
    0.06
     repeated
    0.06
    çļĦæĦıæĢĿæĺ¯
    0.06
    ayar
    0.06
    Activations Density 0.048%

    No Known Activations