© 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. 24252
    Prev
    Next
    INDEX
    Explanations

    India, places, companies

    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
     Icelandic
    -0.08
    åĮ¹
    -0.07
    osz
    -0.07
    rlen
    -0.07
    çIJī
    -0.06
     behaviors
    -0.06
    ä¼ģä¸ļèį£èªī
    -0.06
    ÙĬدÙĬ
    -0.06
    aix
    -0.06
    arcz
    -0.06
    POSITIVE LOGITS
    åį°åº¦
    0.15
     Bhar
    0.14
    åį°åº¦çļĦ
    0.14
     India
    0.13
     Karnataka
    0.13
    India
    0.13
     lakh
    0.13
     Gujarat
    0.13
     Indian
    0.13
     Delhi
    0.13
    Activations Density 1.389%

    No Known Activations