© 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. 12930
    Prev
    Next
    INDEX
    Explanations

    listing countries and nationalities

    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
    åĨµ
    -0.07
    iaux
    -0.06
    åı¯æĥ³
    -0.06
     integration
    -0.06
    /
    -0.05
    åĴ«å°º
    -0.05
    -0.05
    -
    -0.05
    ÃŃk
    -0.05
    ä½ıéĻ¢æ²»çĸĹ
    -0.05
    POSITIVE LOGITS
    å·¥ç¨ĭéĻ¢
    0.09
    åħ¢åħ¢ä¸ļä¸ļ
    0.09
     sonstige
    0.09
    åį«åĨķ
    0.09
    nowrap
    0.09
     иного
    0.09
    ×¢×ķת
    0.08
     ePub
    0.08
    åĭ¤åĭ¤æģ³æģ³
    0.08
     пÑĢоÑĩиÑħ
    0.08
    Activations Density 0.346%

    No Known Activations